© 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. 89900
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ка
    0.57
     في
    0.54
    서
    0.53
    ما
    0.50
    宋
    0.49
    ᄉ
    0.49
    钱包
    0.48
    פר
    0.47
    حديث
    0.46
    اتي
    0.45
    POSITIVE LOGITS
    ation
    0.64
     consonants
    0.60
     cyclones
    0.58
    ctuations
    0.56
     irritability
    0.55
     frustrations
    0.54
     landslides
    0.54
     tantrums
    0.54
     Prothorax
    0.54
     conifers
    0.54
    Activations Density 0.000%

    No Known Activations