© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35622
    Prev
    Next
    INDEX
    Explanations

    up for

    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_11_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
    b
    0.73
     Years
    0.64
    ;
    0.63
    }
    0.62
    জ
    0.61
    Ç
    0.61
    ')
    0.61
    es
    0.60
    {
    0.59
    ­
    0.58
    POSITIVE LOGITS
     гульнявыя
    0.64
    হইবে
    0.60
    ются
    0.59
     variational
    0.59
    ﻞ
    0.59
    ূতন
    0.57
     بیاکتنې
    0.56
    pyrazole
    0.56
    xyplot
    0.56
     postérieures
    0.56
    Activations Density 0.001%

    No Known Activations