© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2388
    Prev
    Next
    INDEX
    Explanations

    SQL queries and code snippets

    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_39_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
    natures
    0.37
    caches
    0.35
    茆
    0.34
     skis
    0.33
     definitiv
    0.33
    沂
    0.33
     tolerant
    0.32
    pitched
    0.32
     ofert
    0.32
    oreau
    0.32
    POSITIVE LOGITS
    iss
    0.30
     Suppl
    0.30
     Bank
    0.29
    習慣
    0.29
    UY
    0.29
    慣
    0.29
    DO
    0.29
    Bank
    0.29
    मौ
    0.29
    cb
    0.28
    Activations Density 0.006%

    No Known Activations