© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11518
    Prev
    Next
    INDEX
    Explanations

    variable declarations and final decisions

    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_13_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
    |
    0.55
    |=
    0.54
     Эта
    0.54
    وحة
    0.54
    ът
    0.51
     systematically
    0.51
     осигурање
    0.50
     (~
    0.50
    |=\
    0.50
    ющие
    0.49
    POSITIVE LOGITS
    hybrid
    0.57
    𝙥
    0.57
    Lam
    0.55
    series
    0.55
    Thompson
    0.54
    大当たり
    0.54
    peria
    0.53
    Res
    0.52
     받았
    0.51
    No
    0.51
    Activations Density 0.049%

    No Known Activations