© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12241
    Prev
    Next
    INDEX
    Explanations

    code and library related tokens

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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>
    -2.53
    '
    -0.77
    ’
    -0.62
    A
    -0.52
     the
    -0.52
    The
    -0.52
    In
    -0.50
    2
    -0.49
    1
    -0.48
    B
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.75
    DispatchToProps
    0.68
    WaitGroup
    0.62
    ioutil
    0.61
     numerus
    0.60
    InSection
    0.57
     uintptr
    0.56
     combineReducers
    0.56
    estream
    0.56
    ollectionView
    0.55
    Activations Density 0.218%

    No Known Activations