© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13228
    Prev
    Next
    INDEX
    Explanations

    words in political, social, and legal contexts that express disagreement or discontent

    oai_token-act-pair · gemini-2.0-flash

    say "from"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    resizingMask
    -0.63
     &___
    -0.60
     autorytatywna
    -0.59
     InputDecoration
    -0.50
     AllAfrica
    -0.49
    Петер
    -0.49
    Obrázky
    -0.47
    prefixer
    -0.46
    ксу
    -0.46
    Enllaces
    -0.45
    POSITIVE LOGITS
     from
    2.52
    from
    1.99
     FROM
    1.75
     From
    1.73
    From
    1.69
     från
    1.63
     dari
    1.58
    จาก
    1.54
     từ
    1.53
    FROM
    1.49
    Activations Density 4.715%

    No Known Activations