© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233712
    Prev
    Next
    INDEX
    Explanations

    gym memberships

    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_32_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
     👍
    0.40
     फ़ोन
    0.37
     aerosol
    0.36
     Slim
    0.36
    迷
    0.35
     dimmer
    0.35
     liters
    0.35
     地址
    0.35
     ईमित्र
    0.35
    ➚
    0.35
    POSITIVE LOGITS
     recession
    0.41
     Homestead
    0.40
     Greek
    0.39
    Greek
    0.39
    registry
    0.39
     homestead
    0.38
    물의
    0.38
    വരുടെ
    0.38
    Und
    0.37
     Mississippi
    0.36
    Activations Density 0.001%

    No Known Activations