© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11862
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in formal reports or press releases

    oai_token-act-pair · gemini-2.0-flash

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.63
    enumi
    -0.46
    Sc
    -0.42
     sc
    -0.39
     Sc
    -0.39
     limiti
    -0.38
     descomp
    -0.38
     Still
    -0.37
    ios
    -0.37
    PRI
    -0.35
    POSITIVE LOGITS
    SourceChecksum
    0.96
    ValueStyle
    0.80
    CloseOperation
    0.78
     uſ
    0.73
     transfieras
    0.71
    AntiForgeryToken
    0.71
     $_"
    0.71
    INCREF
    0.70
    ^(@)
    0.70
    GOTREF
    0.69
    Activations Density 1.131%

    No Known Activations