© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49000
    Prev
    Next
    INDEX
    Explanations

    say "b"

    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_55_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
    chaoxing
    0.40
    Населення
    0.37
     hectares
    0.37
     రూపాయ
    0.36
    %";
    0.35
    %",
    0.35
    Литература
    0.35
     लापरवाही
    0.34
     liters
    0.34
     покажу
    0.34
    POSITIVE LOGITS
    abila
    0.40
    ુપ
    0.40
    so
    0.40
     vài
    0.37
    𝕟
    0.35
    nell
    0.34
    tr
    0.34
    dom
    0.34
    తె
    0.33
    yser
    0.33
    Activations Density 0.006%

    No Known Activations