© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115635
    Prev
    Next
    INDEX
    Explanations

    announcements and offerings

    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_27_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
     interiors
    0.38
     entities
    0.36
    整体
    0.35
     স্পষ্ট
    0.34
    ଘ
    0.33
     styles
    0.33
     qubits
    0.33
     edibles
    0.33
     collectives
    0.33
     primaries
    0.33
    POSITIVE LOGITS
     станет
    0.36
    CRIPTION
    0.35
     glu
    0.34
     новое
    0.34
    iscus
    0.33
    추
    0.33
     جديدة
    0.33
     nuova
    0.33
    glu
    0.33
    asına
    0.33
    Activations Density 0.000%

    No Known Activations