© 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. 35791
    Prev
    Next
    INDEX
    Explanations

    shrouded in

    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
    ه
    0.66
     compless
    0.60
     wers
    0.59
    注意事项
    0.58
    http
    0.57
     afficher
    0.57
     complémentaires
    0.57
    لاع
    0.56
     complexe
    0.55
    오는
    0.55
    POSITIVE LOGITS
     Boots
    0.59
    ྱ
    0.54
    ла
    0.53
    риа
    0.53
    ם
    0.52
    ṣ
    0.52
    kerja
    0.52
     litre
    0.52
    got
    0.52
     آف
    0.50
    Activations Density 0.001%

    No Known Activations