© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102426
    Prev
    Next
    INDEX
    Explanations

    national dish of, capital of

    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_16_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
    გ
    0.48
    scoped
    0.47
    Κ
    0.47
    DOMContentLoaded
    0.47
    際は
    0.47
    実際に
    0.46
     '
    0.46
    sk
    0.45
    zię
    0.45
    名稱
    0.45
    POSITIVE LOGITS
    徠
    0.58
     hale
    0.57
     परवानगी
    0.55
     buddhav
    0.54
    ౪
    0.54
     diurnal
    0.52
     অনুমতি
    0.50
     paradoxical
    0.50
    Fols
    0.49
    鵠
    0.49
    Activations Density 0.025%

    No Known Activations