© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10079
    Prev
    Next
    INDEX
    Explanations

    markups, table formatting, and journal article references

    oai_token-act-pair · gemini-2.0-flash

    cccccc

    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
     Abp
    -0.49
    Abp
    -0.49
     Reason
    -0.47
     Италијани
    -0.47
     parete
    -0.46
     numé
    -0.45
    Vidu
    -0.43
     nö
    -0.43
     uscita
    -0.43
    InSection
    -0.42
    POSITIVE LOGITS
     bezeichneter
    0.89
     дописавши
    0.77
    awtextra
    0.73
    Демографія
    0.66
    etheless
    0.66
     nakalista
    0.66
     beginnetje
    0.64
    Geplaatst
    0.63
    .*")]
    0.62
    prefixer
    0.62
    Activations Density 0.829%

    No Known Activations