© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14697
    Prev
    Next
    INDEX
    Explanations

    wear and tear

    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
    ค
    0.54
    \
    0.52
    CT
    0.51
    Certification
    0.49
    ัว
    0.47
    Meal
    0.46
     ICO
    0.46
    $
    0.46
    ਿਕ
    0.46
    .
    0.46
    POSITIVE LOGITS
     زمانے
    0.69
     reparar
    0.62
    摩擦
    0.62
    秚
    0.60
     abrasive
    0.59
     耐
    0.57
    耐久
    0.57
     durable
    0.56
     విషయం
    0.55
    bulldozer
    0.55
    Activations Density 0.030%

    No Known Activations