© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53879
    Prev
    Next
    INDEX
    Explanations

    code structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    <h4>
    0.49
    ({});
    0.42
     olmadığı
    0.40
    ഞ്ച
    0.39
    NSY
    0.38
    鱒
    0.37
     jaunâtre
    0.37
     férias
    0.36
    鏻
    0.35
    హ్
    0.35
    POSITIVE LOGITS
    ++]
    0.41
    +}
    0.40
     Cross
    0.39
    +
    0.38
     Dynam
    0.37
    ++
    0.37
    \...
    0.37
    +\
    0.37
     wh
    0.36
     Sit
    0.36
    Activations Density 0.000%

    No Known Activations