© 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. 38332
    Prev
    Next
    INDEX
    Explanations

    tokenizer

    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
    ه
    0.96
    a
    0.67
    noop
    0.62
    া
    0.62
    an
    0.61
    ان
    0.59
     결방
    0.55
    cheidung
    0.54
    rien
    0.54
    及时
    0.54
    POSITIVE LOGITS
     trzech
    0.79
     zwią
    0.77
     części
    0.75
     doskona
    0.75
     dangereux
    0.74
     commerciaux
    0.74
    ശ
    0.73
     dwóch
    0.71
    ﺔ
    0.70
     kıs
    0.70
    Activations Density 0.002%

    No Known Activations