© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196082
    Prev
    Next
    INDEX
    Explanations

    defining functions (define, defn)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     españ
    0.14
     థ
    0.14
    ط
    0.14
    ОР
    0.14
    خ
    0.13
    Ц
    0.13
    정이
    0.13
    از
    0.13
    专业
    0.13
    öh
    0.12
    POSITIVE LOGITS
    in
    0.17
    यों
    0.14
    e
    0.14
     behest
    0.14
    as
    0.14
    i
    0.14
    al
    0.14
    -
    0.14
    ie
    0.13
    iella
    0.13
    Activations Density 0.002%

    No Known Activations