© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38924
    Prev
    Next
    INDEX
    Explanations

    care instructions and plans

    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
    ig
    0.71
    kého
    0.70
    น
    0.64
     (
    0.63
    ud
    0.61
    kala
    0.61
    EN
    0.60
    ;
    0.60
    kten
    0.57
    essä
    0.57
    POSITIVE LOGITS
    ある
    0.89
    こと
    0.71
    positroid
    0.70
     aswell
    0.69
    ą
    0.68
     junio
    0.66
     octobre
    0.66
    お問い合わせ
    0.65
    ви
    0.64
     avocat
    0.64
    Activations Density 0.001%

    No Known Activations