© 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. 33628
    Prev
    Next
    INDEX
    Explanations

    page views

    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
    [
    0.88
    <
    0.79
    >
    0.77
    ে
    0.73
     by
    0.70
    <0x8F>
    0.69
     poetic
    0.69
     elke
    0.66
     “
    0.65
    ו
    0.65
    POSITIVE LOGITS
    ری
    0.80
    к
    0.79
    c
    0.68
     individuo
    0.68
    ोनेशिया
    0.68
     individuos
    0.68
     کمار
    0.68
     abrigo
    0.68
     انڈیا
    0.66
    in
    0.66
    Activations Density 0.001%

    No Known Activations