© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11559
    Prev
    Next
    INDEX
    Explanations

    code declarations with the word "public"

    oai_token-act-pair · gemini-2.0-flash

    public or private

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    issu
    -0.47
     lại
    -0.46
     us
    -0.46
     cứ
    -0.46
     tham
    -0.45
    <>
    -0.44
     تعالى
    -0.44
     as
    -0.44
     đúng
    -0.44
    chafts
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.85
     AssemblyTitle
    0.79
     consultato
    0.76
    ReusableCell
    0.74
    MigrationBuilder
    0.74
    lapsingToolbar
    0.68
    出版年
    0.67
     שוליים
    0.67
     Мексичка
    0.66
    EndContext
    0.66
    Activations Density 0.317%

    No Known Activations