© 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. 18144
    Prev
    Next
    INDEX
    Explanations

    main course

    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
     clocks
    0.48
     što
    0.47
     schimb
    0.43
    v
    0.43
     z
    0.42
     މ
    0.42
     kritis
    0.42
     ž
    0.42
     ana
    0.42
     zwr
    0.42
    POSITIVE LOGITS
    peanut
    0.41
    osphère
    0.37
    packaged
    0.37
    lasting
    0.37
    ract
    0.37
    pu
    0.36
    ppu
    0.35
    ρεί
    0.34
    xyplot
    0.34
    stash
    0.34
    Activations Density 0.008%

    No Known Activations