© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176392
    Prev
    Next
    INDEX
    Explanations

    next

    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_50_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
    elv
    0.38
     URLs
    0.38
    idora
    0.37
     PCBs
    0.37
     Lat
    0.37
    }--\
    0.37
     রা
    0.37
     GSM
    0.36
     माला
    0.36
     ASPECTS
    0.36
    POSITIVE LOGITS
    ленном
    0.38
     গো
    0.37
    iciembre
    0.36
     दोन
    0.36
     belonged
    0.35
     zwei
    0.34
    ;/
    0.34
    isins
    0.34
    ليات
    0.34
    ရိ
    0.34
    Activations Density 0.001%

    No Known Activations