© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially javascript, containing the word 'delete'

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or object properties

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

    coding and programming

    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
     cos
    -0.49
     comp
    -0.49
     entre
    -0.46
     pr
    -0.43
     cro
    -0.42
     f
    -0.42
     pos
    -0.40
     sinh
    -0.40
    netz
    -0.40
     ver
    -0.39
    POSITIVE LOGITS
    AnchorStyles
    0.85
    extAlignment
    0.84
     chré
    0.83
     ainfi
    0.81
     <=",
    0.79
     avoient
    0.79
     Efq
    0.79
    Clik
    0.78
     russes
    0.78
     isolé
    0.77
    Activations Density 0.226%

    No Known Activations