© 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. 86096
    Prev
    Next
    INDEX
    Explanations

    scientific terms, unrelated words

    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
    il
    0.80
    an
    0.78
    sw
    0.77
    त
    0.76
    n
    0.75
    r
    0.75
    B
    0.74
    ล
    0.73
    T
    0.73
    I
    0.73
    POSITIVE LOGITS
    не
    0.90
    ána
    0.79
    ני
    0.77
     একমাত্র
    0.77
    ă
    0.76
    你
    0.75
    ена
    0.73
     accéder
    0.73
    اني
    0.72
    ጠበ
    0.71
    Activations Density 0.000%

    No Known Activations