© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16014
    Prev
    Next
    INDEX
    Explanations

    towards a person or thing

    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_15_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
    啧
    0.57
     OF
    0.52
    प
    0.52
     মিলি
    0.49
     ಮುಂದೆ
    0.48
     */
    0.47
     ;-)
    0.46
    **************/
    0.46
    ણમાં
    0.46
     MULT
    0.45
    POSITIVE LOGITS
     आफ्नो
    0.63
     аутох
    0.59
     પોતાના
    0.57
     svého
    0.55
     svoje
    0.55
     ĝi
    0.55
     своего
    0.54
     gaat
    0.53
     svog
    0.52
    iyet
    0.52
    Activations Density 0.004%

    No Known Activations