© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40847
    Prev
    Next
    INDEX
    Explanations

    date labels, headers, or column 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_11_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
    W
    0.72
    an
    0.70
    on
    0.69
    i
    0.69
    z
    0.66
    iz
    0.66
    what
    0.66
    N
    0.66
    P
    0.64
    ان
    0.63
    POSITIVE LOGITS
     والس
    0.55
     TRIG
    0.54
     보다
    0.54
     смо
    0.51
     поя
    0.50
     روس
    0.49
    љи
    0.48
     секрета
    0.48
     为了
    0.48
     наси
    0.47
    Activations Density 0.006%

    No Known Activations