© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66792
    Prev
    Next
    INDEX
    Explanations

    sea ice

    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_41_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
     P
    0.71
     Pen
    0.60
    クラブ
    0.49
     П
    0.48
     Club
    0.47
    Pen
    0.47
     pen
    0.46
     พ
    0.45
     क्लब
    0.45
     Пен
    0.44
    POSITIVE LOGITS
     ice
    0.66
     pack
    0.61
     Ice
    0.57
    Ice
    0.54
    Pack
    0.53
     Pack
    0.53
    冰
    0.53
    アイス
    0.50
    氷
    0.50
    pack
    0.50
    Activations Density 0.012%

    No Known Activations