© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38595
    Prev
    Next
    INDEX
    Explanations

    wrestling with

    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_11_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
     Percy
    0.67
     thờ
    0.63
     momencie
    0.61
     DSLR
    0.61
     Wheat
    0.60
     persecuted
    0.58
     {
    0.57
     difer
    0.57
     Yesterday
    0.57
     Phong
    0.57
    POSITIVE LOGITS
    ان
    0.64
    海
    0.59
    ل
    0.59
    ᑖ
    0.59
     attainment
    0.59
    partum
    0.58
    コ
    0.58
    اد
    0.56
    enames
    0.55
    y
    0.55
    Activations Density 0.002%

    No Known Activations