© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99634
    Prev
    Next
    INDEX
    Explanations

    bipartisan, brainstorm, tools, preprocess, fat

    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_16_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
     And
    0.54
     Ibrahim
    0.52
    检
    0.51
    Pressed
    0.49
    ពិសេស
    0.47
     But
    0.47
     an
    0.47
     Adjusted
    0.47
    But
    0.46
     IBS
    0.46
    POSITIVE LOGITS
    ენ
    0.51
    ет
    0.48
    フィック
    0.47
    гей
    0.47
    ローブ
    0.47
     де
    0.46
    ي
    0.45
    ونکو
    0.45
    ى
    0.44
     comod
    0.44
    Activations Density 0.000%

    No Known Activations