© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31678
    Prev
    Next
    INDEX
    Explanations

    say OR

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     помо
    0.43
     ха
    0.39
    깨
    0.39
    פשר
    0.38
     Baj
    0.38
     cellulaire
    0.38
     ponto
    0.37
    ിക്കു
    0.37
     suffis
    0.37
    िफ्ट
    0.36
    POSITIVE LOGITS
    ga
    0.52
    Ga
    0.38
    гель
    0.38
    镓
    0.38
    gels
    0.38
    bearer
    0.37
    ගත්
    0.37
    леты
    0.37
    gax
    0.37
    heath
    0.37
    Activations Density 0.000%

    No Known Activations