© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    words that end with a vowel followed by one or more consonants

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'c' or 'd'

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

    vanqu

    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
    SharedDtor
    -0.90
    ValueStyle
    -0.88
    الإنجليزية
    -0.80
    InjectAttribute
    -0.78
    AutoresizingMask
    -0.75
    RenderAtEndOf
    -0.75
    Personensuche
    -0.74
    RectangleBorder
    -0.74
     للاسماء
    -0.72
     betweenstory
    -0.71
    POSITIVE LOGITS
     c
    0.49
    失
    0.46
    hagen
    0.45
    annel
    0.45
     d
    0.42
     ber
    0.42
     emosi
    0.41
     sesso
    0.41
    viaf
    0.41
    しょ
    0.41
    Activations Density 6.896%

    No Known Activations