© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34112
    Prev
    Next
    INDEX
    Explanations

    list item or code delimiters

    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_31_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
     oov
    0.30
    ুধ
    0.30
     ذریع
    0.30
    পূর্বক
    0.30
    <0xB0>
    0.29
    ліза
    0.29
    alen
    0.29
    রফ
    0.29
    sentence
    0.29
    ро
    0.29
    POSITIVE LOGITS
     Ronnie
    0.33
    飪
    0.32
    ंकडून
    0.31
    ถา
    0.31
     выяв
    0.31
     Geology
    0.31
    тили
    0.31
     అక్కడ
    0.31
    ⑭
    0.30
     trouvé
    0.30
    Activations Density 0.014%

    No Known Activations