© 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. 66781
    Prev
    Next
    INDEX
    Explanations

    cutting, clipping, or segments

    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
    ^{*}+
    0.40
    тировать
    0.39
    ᅲ
    0.38
    osevelt
    0.37
     trains
    0.36
     rigid
    0.36
     चा
    0.35
     predicates
    0.35
     സമ
    0.34
     식
    0.34
    POSITIVE LOGITS
     cuttings
    1.36
     clippings
    1.32
     clipping
    1.22
     Clipping
    1.14
     Cli
    1.06
    Cli
    1.02
     clipped
    0.84
     clip
    0.83
    ings
    0.82
    Clip
    0.82
    Activations Density 0.039%

    No Known Activations