© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216801
    Prev
    Next
    INDEX
    Explanations

    in [location/field/time]

    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_31_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
    YAN
    0.36
     মুসলমানদের
    0.36
     leaks
    0.35
     ހ
    0.35
     koristi
    0.35
     pinched
    0.34
    }\}$.
    0.34
     continuously
    0.33
    removeFrom
    0.33
     agarose
    0.33
    POSITIVE LOGITS
     sensations
    0.41
    oriented
    0.36
    Graphics
    0.34
    gll
    0.34
    GCC
    0.33
     departments
    0.33
    graphics
    0.32
     bacterial
    0.32
     Graphics
    0.32
    舘
    0.32
    Activations Density 0.002%

    No Known Activations