© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220307
    Prev
    Next
    INDEX
    Explanations

    bootstrap css/js links and classes

    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_31_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
     కారణంగా
    0.41
    frast
    0.41
     belast
    0.40
    зовая
    0.40
    }}}
    0.37
     aline
    0.37
     شخصیت
    0.36
    Kant
    0.36
    㣱
    0.36
     √
    0.36
    POSITIVE LOGITS
     precursors
    0.41
    ="//
    0.40
    heads
    0.37
     issuers
    0.37
    ype
    0.37
     solvers
    0.36
     compilers
    0.36
     writers
    0.36
     तंत्र
    0.36
     expects
    0.36
    Activations Density 0.000%

    No Known Activations