© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134929
    Prev
    Next
    INDEX
    Explanations

    identification numbers

    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_37_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
     modalities
    0.64
    各種
    0.58
     formats
    0.56
    ต่างๆ
    0.56
    諸
    0.54
    诸
    0.54
    各类
    0.53
    Various
    0.52
     genres
    0.51
    各大
    0.51
    POSITIVE LOGITS
     कलम
    0.38
    ioni
    0.36
    rung
    0.36
     plu
    0.36
    iz
    0.35
     \&
    0.35
     komb
    0.35
     tantôt
    0.35
     Grave
    0.35
     pierwsze
    0.35
    Activations Density 0.056%

    No Known Activations