© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56925
    Prev
    Next
    INDEX
    Explanations

    waist

    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_11_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
    Θ
    0.62
    H
    0.61
    B
    0.60
    le
    0.59
    K
    0.59
    f
    0.58
    lay
    0.57
    Q
    0.57
    at
    0.57
    J
    0.57
    POSITIVE LOGITS
     pathMatch
    0.61
    èque
    0.60
    '`--'`--
    0.57
    SecurityMarks
    0.55
    ッティング
    0.55
    駆け
    0.55
    ミック
    0.54
     알고
    0.53
     حقیقی
    0.53
    getBlueTeam
    0.53
    Activations Density 0.001%

    No Known Activations