© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2993
    Prev
    Next
    INDEX
    Explanations

    code related file types (i.e. h, c, php)

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    omiast
    -0.58
    eddable
    -0.58
    anskje
    -0.57
    endphp
    -0.56
    jfree
    -0.56
    GraphicsUnit
    -0.55
     الدولى
    -0.55
     autorytatywna
    -0.55
    OSPITAL
    -0.54
    bitat
    -0.54
    POSITIVE LOGITS
    Portale
    0.56
     Paglinawan
    0.47
    uxxxx
    0.47
    DockStyle
    0.46
    BaseType
    0.44
    のが
    0.43
    HideFlags
    0.43
     виправивши
    0.43
     ory
    0.42
     balanceOf
    0.42
    Activations Density 15.426%

    No Known Activations