© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104585
    Prev
    Next
    INDEX
    Explanations

    DataFrame variable names

    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_1_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
    1
    1.02
    n
    0.92
    2
    0.76
    ek
    0.71
     Excess
    0.71
    ICKS
    0.71
    ;
    0.70
    ID
    0.69
     repris
    0.68
     for
    0.65
    POSITIVE LOGITS
     is
    0.90
    的
    0.80
    い
    0.79
    まり
    0.77
    с
    0.77
    ονται
    0.68
     سے
    0.67
    пление
    0.67
    п
    0.66
    ایی
    0.64
    Activations Density 0.002%

    No Known Activations