© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60888
    Prev
    Next
    INDEX
    Explanations

    ant

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    al
    1.15
    an
    1.05
    on
    0.91
    ان
    0.82
    া
    0.70
    a
    0.68
    u
    0.67
    in
    0.66
    es
    0.64
    en
    0.60
    POSITIVE LOGITS
    ગ્ર
    0.39
     totalement
    0.38
     rained
    0.38
    onavir
    0.37
    abr
    0.37
     douloureuse
    0.37
    wadi
    0.37
    ㎏
    0.36
     auquel
    0.36
     ப
    0.36
    Activations Density 0.001%

    No Known Activations