© 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. 54461
    Prev
    Next
    INDEX
    Explanations

    Here

    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
    Breakpoint
    0.40
    断
    0.39
    破
    0.39
     Toler
    0.38
    ཁ
    0.38
    唥
    0.38
     republics
    0.38
    ុក
    0.38
    Bullet
    0.37
     tolerancia
    0.37
    POSITIVE LOGITS
     பார்க்கலாம்
    0.39
     caloric
    0.38
     connaissance
    0.37
     สัก
    0.37
    pertoire
    0.37
     ँ
    0.37
     রহিয়াছে
    0.37
     যারা
    0.36
     pärast
    0.36
     serialize
    0.36
    Activations Density 0.020%

    No Known Activations