© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131976
    Prev
    Next
    INDEX
    Explanations

    code comments or examples

    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_6_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
    t
    1.53
    el
    1.12
    d
    1.12
    en
    0.94
    us
    0.87
    ছে
    0.86
    h
    0.86
    g
    0.82
    時間
    0.80
    지
    0.80
    POSITIVE LOGITS
     that
    1.08
    that
    1.04
    ،
    0.96
    ;
    0.95
    ?
    0.94
    "
    0.86
    ।
    0.85
    0.82
    는
    0.81
    !
    0.81
    Activations Density 0.027%

    No Known Activations