© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53464
    Prev
    Next
    INDEX
    Explanations

    specific concepts

    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_55_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
    лм
    0.38
    hä
    0.37
     жал
    0.37
    水
    0.35
    皓
    0.35
    ysm
    0.35
    츰
    0.35
     Hä
    0.34
    யம்
    0.34
    water
    0.33
    POSITIVE LOGITS
     Anger
    0.41
    barS
    0.41
    galo
    0.41
    WebSocket
    0.39
    রুখ
    0.38
     ओन
    0.38
    ندن
    0.38
     inflate
    0.38
     ERR
    0.36
     подар
    0.36
    Activations Density 0.005%

    No Known Activations