© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14336
    Prev
    Next
    INDEX
    Explanations

    academic paper requirements

    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_13_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
    者
    0.50
    ers
    0.49
    เล
    0.47
    PLATE
    0.47
     home
    0.46
     mittens
    0.46
     sleek
    0.45
     असली
    0.45
     coalesce
    0.45
    aktual
    0.44
    POSITIVE LOGITS
    at
    0.50
    abit
    0.49
    heden
    0.48
    </h6>
    0.46
     Argu
    0.46
     Dynam
    0.45
     学
    0.45
     সন্ন
    0.45
     ധ
    0.44
     UF
    0.44
    Activations Density 0.053%

    No Known Activations