© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57273
    Prev
    Next
    INDEX
    Explanations

    inspect browser developer tools

    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_11_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
    iei
    0.53
    color
    0.52
    iberg
    0.52
    ?
    0.50
    î
    0.50
    vore
    0.49
    tocol
    0.49
    ammens
    0.49
    fo
    0.48
    year
    0.48
    POSITIVE LOGITS
     wastes
    0.44
     ACTUAL
    0.44
    ால
    0.43
    ਗ
    0.43
     aço
    0.42
     jueces
    0.42
     fleshy
    0.42
     analyzed
    0.42
     optimised
    0.42
    𝓗
    0.42
    Activations Density 0.004%

    No Known Activations