© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24662
    Prev
    Next
    INDEX
    Explanations

    versions of software or technology

    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_10_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
    s
    1.02
     to
    0.81
    (
    0.80
    es
    0.80
    ss
    0.73
    sla
    0.71
     et
    0.66
     attic
    0.65
    polls
    0.65
     unanswered
    0.64
    POSITIVE LOGITS
    𝓉
    0.67
    ي
    0.64
    ੋ
    0.63
    犷
    0.62
    женности
    0.61
    𝓎
    0.60
    ë
    0.59
    ο
    0.58
    事項
    0.57
     creazione
    0.57
    Activations Density 0.010%

    No Known Activations