© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12506
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords related to programming/scripting, particularly C and Javascript

    oai_token-act-pair · gemini-2.0-flash

    signals and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ="@+
    -0.78
     Eſ
    -0.71
     Reſ
    -0.66
     numberWith
    -0.66
    исленность
    -0.66
     ſta
    -0.65
    GraphicsUnit
    -0.65
     whoſe
    -0.63
     poffe
    -0.63
     ſtre
    -0.61
    POSITIVE LOGITS
    CodedInputStream
    0.63
    GEBURTSDATUM
    0.61
    UTERS
    0.50
    adaptiveStyles
    0.48
    errHandler
    0.48
    DeleteBehavior
    0.47
     layui
    0.42
    oredCriteria
    0.42
    ModelSerializer
    0.41
    principalColumn
    0.41
    Activations Density 4.755%

    No Known Activations