© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143866
    Prev
    Next
    INDEX
    Explanations

    Black, Brown, Bantu

    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_0_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
    し
    1.77
    ne
    1.69
    ter
    1.65
    l
    1.63
    de
    1.61
    st
    1.60
    da
    1.58
    land
    1.56
    ng
    1.52
    der
    1.45
    POSITIVE LOGITS
    ;
    1.35
    ٠
    1.35
     flamboyant
    1.31
    ج
    1.31
     Código
    1.30
    \%),
    1.28
    큥
    1.27
    ويل
    1.26
     libres
    1.24
    getMainUI
    1.24
    Activations Density 0.000%

    No Known Activations