© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204343
    Prev
    Next
    INDEX
    Explanations

    say "i" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    JA
    0.37
    activation
    0.36
    FI
    0.36
     halide
    0.36
    jaer
    0.34
    écoute
    0.34
    榜
    0.34
    лее
    0.34
     வி
    0.34
    adr
    0.34
    POSITIVE LOGITS
    欷
    0.40
    зем
    0.40
     Dug
    0.40
    Defense
    0.39
    Dup
    0.38
    భ్య
    0.38
     Associates
    0.37
     Али
    0.36
    Thể
    0.36
    imiya
    0.36
    Activations Density 0.000%

    No Known Activations