© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220339
    Prev
    Next
    INDEX
    Explanations

    clip breaking

    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
    ɥ
    0.25
    वरुन
    0.24
     collapses
    0.24
    ሙሉ
    0.23
     collapse
    0.22
    Demand
    0.22
     Cermak
    0.22
    Without
    0.22
     collapsing
    0.22
     μέσω
    0.22
    POSITIVE LOGITS
    푼
    0.24
     シャツ
    0.22
     проблемы
    0.22
    getpath
    0.21
    ప్పు
    0.20
     obstruct
    0.20
    ladder
    0.20
     README
    0.20
    getPath
    0.20
    tickers
    0.20
    Activations Density 0.000%

    No Known Activations