© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134230
    Prev
    Next
    INDEX
    Explanations

    set command

    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_1_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
    ۔
    1.42
    {
    1.30
    :
    1.23
    。
    1.23
    ।
    1.17
    .
    1.13
    $.
    1.12
    gi
    1.10
    ።
    1.00
     -
    0.99
    POSITIVE LOGITS
    на
    1.68
    น
    1.12
    я
    1.05
    ാ
    1.00
    ير
    0.98
    от
    0.96
    agę
    0.96
    ා
    0.95
     deuxième
    0.91
     hadden
    0.91
    Activations Density 0.003%

    No Known Activations