© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58456
    Prev
    Next
    INDEX
    Explanations

    traditionally associated with

    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_11_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
    o
    0.67
    ']=
    0.55
     Antibiot
    0.55
    f
    0.50
    ps
    0.48
    נת
    0.48
    ;')
    0.46
    ף
    0.46
    cnt
    0.46
    c
    0.46
    POSITIVE LOGITS
     didn
    0.65
    тта
    0.60
    That
    0.59
     erred
    0.59
     conteúdo
    0.57
     told
    0.57
     fortitude
    0.56
     misled
    0.56
     weren
    0.55
     comprend
    0.54
    Activations Density 0.009%

    No Known Activations