© 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. 10537
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions that connect concepts in language, with a particular emphasis on "all", "that", "from", "for", and "to" when co-located with other words that help form complete phrases.

    oai_token-act-pair · gemini-2.0-flash

    major

    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
    省市镇
    -0.83
     للمعارف
    -0.74
     AssemblyCulture
    -0.67
    ,‎
    -0.64
     архивлан
    -0.61
     vPvB
    -0.61
    InjectAttribute
    -0.61
    AutoScaleMode
    -0.60
    ^(@)
    -0.60
    Personensuche
    -0.59
    POSITIVE LOGITS
     major
    2.44
    major
    2.17
    Major
    1.88
     Major
    1.70
     MAJOR
    1.68
    MAJOR
    1.59
     leading
    1.54
    leading
    1.20
     Leading
    1.16
    Leading
    1.16
    Activations Density 2.674%

    No Known Activations