© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85903
    Prev
    Next
    INDEX
    Explanations

    Kohle, barrier, Foundation

    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_3_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
    旻
    0.61
    at
    0.60
    as
    0.59
    and
    0.58
     nowych
    0.55
    nym
    0.54
     появи
    0.54
    大幅
    0.54
    ną
    0.53
    ach
    0.52
    POSITIVE LOGITS
     in
    0.73
    0.65
     exacerbated
    0.61
    ки
    0.60
     ब
    0.58
     отсут
    0.58
    ス
    0.58
    '।
    0.57
     Eighteenth
    0.57
     disasters
    0.57
    Activations Density 0.000%

    No Known Activations