© 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. 36681
    Prev
    Next
    INDEX
    Explanations

    expertise and interest

    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
    '
    0.94
    r
    0.72
    ders
    0.71
    h
    0.71
    graph
    0.68
    ds
    0.68
    dv
    0.67
    digit
    0.66
    areas
    0.66
    z
    0.64
    POSITIVE LOGITS
     slumped
    0.70
    로
    0.68
    ながら
    0.67
    시
    0.67
    ان
    0.64
    した
    0.64
    と思います
    0.64
     stepped
    0.64
     boomerang
    0.64
     categor
    0.63
    Activations Density 0.027%

    No Known Activations