© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117628
    Prev
    Next
    INDEX
    Explanations

    identifying what seems like

    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_27_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
     الفترة
    0.46
     fundada
    0.38
    詬
    0.38
     Critic
    0.35
     décadas
    0.34
     Tilly
    0.33
    octagon
    0.33
     verloren
    0.33
    ❜
    0.33
    ному
    0.33
    POSITIVE LOGITS
     हार्ड
    0.38
    定
    0.35
     purge
    0.34
    进行
    0.34
     compulsive
    0.33
     manh
    0.33
     cú
    0.33
    [,,"
    0.32
     మా
    0.32
     seizure
    0.32
    Activations Density 0.003%

    No Known Activations