© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232755
    Prev
    Next
    INDEX
    Explanations

    sauce or saucepan

    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_6_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
    form
    1.01
    ’
    0.98
    ”
    0.96
     ပြော
    0.95
    ोच्च
    0.93
    ”).
    0.91
    assignmentItems
    0.88
    familyName
    0.85
    полни
    0.83
     дзяржа
    0.82
    POSITIVE LOGITS
    ER
    1.07
    ING
    0.96
    ED
    0.93
    ان
    0.93
    ad
    0.89
    AN
    0.87
    ES
    0.86
    1
    0.84
    OS
    0.83
     were
    0.80
    Activations Density 0.001%

    No Known Activations