© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9334
    Prev
    Next
    INDEX
    Explanations

    code, likely in C

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.67
     team
    -0.39
     Team
    -0.39
    leetcode
    -0.39
    chen
    -0.38
    fören
    -0.38
     ríos
    -0.37
     beetje
    -0.37
     mise
    -0.36
     Lee
    -0.36
    POSITIVE LOGITS
    WithIOException
    0.84
    ScopeManager
    0.75
    ductory
    0.67
     intptr
    0.65
    GOTREF
    0.65
    ToAction
    0.60
    featureID
    0.60
    endphp
    0.60
    HasOne
    0.59
     unary
    0.58
    Activations Density 0.075%

    No Known Activations