© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150385
    Prev
    Next
    INDEX
    Explanations

    OD

    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_59_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
    M
    0.60
    s
    0.59
    ی
    0.53
    म
    0.52
    b
    0.47
    m
    0.47
    ের
    0.42
    ς
    0.42
     M
    0.42
    eye
    0.41
    POSITIVE LOGITS
     е
    0.43
    RANGE
    0.40
    OCT
    0.39
    IMAGES
    0.39
     MULT
    0.38
    MANAG
    0.38
    MINUTE
    0.38
    SCREEN
    0.38
    CORDS
    0.38
    CROSS
    0.38
    Activations Density 0.000%

    No Known Activations