© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260878
    Prev
    Next
    INDEX
    Explanations

    ST_

    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_22_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
    a
    0.50
    ה
    0.46
     ){
    0.45
     THIS
    0.45
     Valores
    0.44
    ه
    0.44
    which
    0.43
    教
    0.43
    ام
    0.43
    ીએ
    0.43
    POSITIVE LOGITS
     संतान
    0.44
    cies
    0.41
    镜头
    0.41
     కుటుంబ
    0.41
     شاہ
    0.40
    urlString
    0.40
     μουσ
    0.40
    orsz
    0.39
     რა
    0.39
     زوج
    0.39
    Activations Density 0.000%

    No Known Activations