© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15615
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially from system headers and auto-generated code.

    oai_token-act-pair · gemini-2.0-flash

    Code/system files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Xna
    -0.65
    e
    -0.53
     ही
    -0.53
    .
    -0.52
    @
    -0.52
    /
    -0.51
    M
    -0.51
    m
    -0.51
    i
    -0.49
    c
    -0.49
    POSITIVE LOGITS
    Personendaten
    1.21
     autorytatywna
    1.20
    Autoritní
    1.19
    ⓧ
    1.10
    IsContent
    1.00
    Hauptartikel
    1.00
    <bos>
    0.98
    存于互联网档案馆
    0.94
    Personensuche
    0.93
    Datuak
    0.92
    Activations Density 0.723%

    No Known Activations