© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137537
    Prev
    Next
    INDEX
    Explanations

    barcode scanner

    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_12_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
    τυχ
    0.62
     vías
    0.58
    рода
    0.56
    קו
    0.56
     sécher
    0.55
    掣
    0.54
    בות
    0.52
     marchés
    0.51
    къ
    0.51
     phénomène
    0.51
    POSITIVE LOGITS
    ur
    0.59
    log
    0.58
    ar
    0.56
    na
    0.55
     Eurasia
    0.55
    abase
    0.54
    jali
    0.54
    enia
    0.52
    w
    0.52
    $
    0.52
    Activations Density 0.000%

    No Known Activations