© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19097
    Prev
    Next
    INDEX
    Explanations

    language codes (en, es)

    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
    화
    0.57
     Oxidation
    0.56
     oxidation
    0.54
     internazionali
    0.51
     اکتوبر
    0.49
     oxid
    0.49
    regierung
    0.49
    ний
    0.48
    нува
    0.47
    化
    0.47
    POSITIVE LOGITS
     don
    0.62
    im
    0.59
     blonde
    0.57
     ငါ
    0.54
     wrongful
    0.54
     juguete
    0.54
     blem
    0.53
     πισ
    0.53
    ið
    0.52
    epte
    0.51
    Activations Density 0.007%

    No Known Activations