© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37500
    Prev
    Next
    INDEX
    Explanations

    in

    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_57_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
     e
    0.46
     Ins
    0.43
    as
    0.41
    e
    0.40
    ass
    0.40
     Ass
    0.40
    sak
    0.40
    asa
    0.39
     st
    0.38
    s
    0.38
    POSITIVE LOGITS
    idered
    0.48
    rennt
    0.48
    pective
    0.47
    istered
    0.47
    endants
    0.45
    Titanic
    0.44
    ohist
    0.43
    ern
    0.41
    hren
    0.41
    rend
    0.40
    Activations Density 0.016%

    No Known Activations