© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44417
    Prev
    Next
    INDEX
    Explanations

    TSIG, tasers, tarsiers, tachi, Tsiolkovsky

    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
    t
    0.79
    AKE
    0.67
    ZW
    0.65
     Paperback
    0.64
    ;
    0.64
    कल्चर
    0.62
     Synonym
    0.62
    К
    0.62
     Timberwolves
    0.61
    A
    0.61
    POSITIVE LOGITS
    с
    0.71
     hizo
    0.66
    в
    0.63
     jasa
    0.61
     míst
    0.60
     *=
    0.59
     znovu
    0.59
     ciertas
    0.58
     فعل
    0.58
     matrice
    0.57
    Activations Density 0.005%

    No Known Activations