© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88844
    Prev
    Next
    INDEX
    Explanations

    Chamber of Commerce

    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_23_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
     tatto
    0.43
     Carriers
    0.42
     세포
    0.41
    ௐ
    0.41
     ডো
    0.40
     benefícios
    0.40
     seawater
    0.39
     Shee
    0.39
     Stahl
    0.39
     Outs
    0.39
    POSITIVE LOGITS
     приступи
    0.44
    ૂર્વ
    0.41
    pathy
    0.40
    upy
    0.39
     "'";
    0.39
    new
    0.38
     actively
    0.38
    धारी
    0.38
    <h2>
    0.38
    path
    0.37
    Activations Density 0.000%

    No Known Activations