© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36562
    Prev
    Next
    INDEX
    Explanations

    deeply ingrained

    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
    1.02
    j
    0.86
    c
    0.86
    ک
    0.82
    но
    0.78
    v
    0.71
    f
    0.68
     می
    0.67
    h
    0.67
    m
    0.64
    POSITIVE LOGITS
    5
    0.73
    4
    0.70
    ر
    0.70
    ab
    0.69
    ról
    0.67
    ل
    0.67
    积
    0.67
     Nähe
    0.66
    rú
    0.63
    a
    0.63
    Activations Density 0.002%

    No Known Activations