© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43249
    Prev
    Next
    INDEX
    Explanations

    deadlocks

    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_3_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
    t
    0.93
    ا
    0.89
    y
    0.82
    k
    0.76
    as
    0.75
    i
    0.74
    b
    0.72
    h
    0.71
    tól
    0.69
    d
    0.68
    POSITIVE LOGITS
    ία
    0.75
    ین
    0.59
     Familia
    0.59
     Система
    0.57
    ANT
    0.57
     Informations
    0.56
    Action
    0.56
    uste
    0.56
    ಾವಣ
    0.55
    ortex
    0.54
    Activations Density 0.007%

    No Known Activations