© 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. 86890
    Prev
    Next
    INDEX
    Explanations

    Scooby Doo, Rail, Carey, Young, Speed

    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
    ü
    0.78
    ри
    0.76
    Ps
    0.75
    w
    0.69
    ens
    0.68
     في
    0.68
     in
    0.67
    েল
    0.65
    ोटा
    0.65
    yl
    0.64
    POSITIVE LOGITS
    ו
    0.89
    و
    0.76
     herpes
    0.68
     Gori
    0.68
    S
    0.62
     lamang
    0.56
     commandments
    0.56
     Oaxaca
    0.56
     alti
    0.56
    OL
    0.54
    Activations Density 0.000%

    No Known Activations