© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205145
    Prev
    Next
    INDEX
    Explanations

    opening, closed, shop

    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_37_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
    instell
    0.39
    ➨
    0.39
    Execute
    0.37
    🌐
    0.37
     Grounds
    0.36
     cephal
    0.35
    Thin
    0.35
     ресур
    0.35
    西方
    0.34
    ⇉
    0.34
    POSITIVE LOGITS
     opening
    0.50
     street
    0.48
     mở
    0.47
     öpp
    0.47
     abrir
    0.46
     apertura
    0.46
     abertura
    0.46
     स्ट्रीट
    0.46
     Street
    0.46
     ouvrir
    0.44
    Activations Density 0.035%

    No Known Activations