© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1934
    Prev
    Next
    INDEX
    Explanations

    words that express that something is taking place in the present

    oai_token-act-pair · gemini-2.0-flash

    much

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ⓧ
    -0.68
    HtmlAttribute
    -0.63
    more
    -0.56
     indisponible
    -0.56
    Более
    -0.55
     Италијани
    -0.55
    More
    -0.55
     More
    -0.54
     more
    -0.52
    better
    -0.52
    POSITIVE LOGITS
     much
    3.09
    Much
    2.89
    much
    2.89
     Much
    2.75
     MUCH
    2.20
     mucho
    1.81
    mucho
    1.37
     viel
    1.31
     mye
    1.23
     beaucoup
    1.21
    Activations Density 16.832%

    No Known Activations