© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202291
    Prev
    Next
    INDEX
    Explanations

    signal ()

    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_12_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
    л
    0.56
    ح
    0.52
    력
    0.52
    sa
    0.51
    ן
    0.49
    وح
    0.49
    스
    0.48
    บ
    0.48
    7
    0.47
    ל
    0.47
    POSITIVE LOGITS
     annum
    0.51
     ø
    0.48
     škola
    0.47
     iunie
    0.47
     océano
    0.47
    као
    0.47
     inicialmente
    0.46
    បង្ហ
    0.45
     период
    0.45
     ethereal
    0.45
    Activations Density 0.002%

    No Known Activations