© 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. 39491
    Prev
    Next
    INDEX
    Explanations

    rotavirus vaccine or rotary dial

    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
    ای
    0.73
    and
    0.73
    avano
    0.69
    пто
    0.66
    وک
    0.65
    떻
    0.65
    ق
    0.64
    in
    0.63
    Quanto
    0.63
    You
    0.63
    POSITIVE LOGITS
     rot
    1.12
     Rot
    0.95
     rotary
    0.79
     rotational
    0.72
     Rotary
    0.71
     roti
    0.70
     ROT
    0.68
     baseball
    0.68
     ,
    0.68
     (
    0.67
    Activations Density 0.001%

    No Known Activations