© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215008
    Prev
    Next
    INDEX
    Explanations

    different scripts languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     ज़
    0.38
    લી
    0.38
    invariant
    0.37
    luss
    0.37
     columnIndex
    0.36
    ള
    0.36
    </em>
    0.36
    лай
    0.36
    ussel
    0.36
    sqlite
    0.35
    POSITIVE LOGITS
     Tran
    0.40
     داد
    0.38
    Cheese
    0.38
     tran
    0.38
     Cheese
    0.37
     stad
    0.37
     ಎರ
    0.37
    🇰
    0.37
     repulsive
    0.37
     Kanji
    0.36
    Activations Density 0.013%

    No Known Activations