© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6226
    Prev
    Next
    INDEX
    Explanations

    a weird mix of auxiliary verbs ('is', 'are', 'was', 'will', 'had'), to connectives ('to', 'with', 'and') and also personal pronouns ('he', 'she')

    oai_token-act-pair · gemini-2.0-flash

    words related to volunteer assistance

    np_token-act-pair-logits · gpt-4o-mini

    Computer Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istin
    -0.41
    lä
    -0.40
    Geplaatst
    -0.39
     consulter
    -0.39
     defining
    -0.39
     Editor
    -0.37
     пар
    -0.37
    fficient
    -0.36
     dejando
    -0.36
    Published
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.83
    httphttps
    0.82
    SequentialGroup
    0.80
    tvguidetime
    0.79
    saraba
    0.78
    ChildScrollView
    0.78
    :+:
    0.77
     operate
    0.76
     tartalomajánló
    0.75
     ويكيميديا
    0.71
    Activations Density 2.534%

    No Known Activations