© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172978
    Prev
    Next
    INDEX
    Explanations

    leadership roles

    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_20_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
    acca
    0.40
    sey
    0.36
     literature
    0.36
    чного
    0.36
    ቼ
    0.36
    literature
    0.35
    ського
    0.34
    شت
    0.34
     treating
    0.34
    ської
    0.34
    POSITIVE LOGITS
     }{}_{\
    0.41
     Dighe
    0.38
     feat
    0.36
    Col
    0.35
     தேவை
    0.34
    ័រ
    0.34
     पॉप
    0.34
     ຮ
    0.34
     Sal
    0.33
     बनाम
    0.33
    Activations Density 0.001%

    No Known Activations