© 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. 124298
    Prev
    Next
    INDEX
    Explanations

    USC and SD codes

    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
    ,
    0.73
    -
    0.72
    aman
    0.71
    ing
    0.70
     i
    0.69
    oul
    0.69
    el
    0.69
    ase
    0.69
    ()
    0.69
     they
    0.68
    POSITIVE LOGITS
    티
    0.74
    お
    0.70
    いわ
    0.70
    in
    0.68
     práctica
    0.68
    し
    0.68
     tất
    0.67
    其他
    0.66
    ид
    0.66
    いろいろ
    0.66
    Activations Density 0.002%

    No Known Activations