© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248686
    Prev
    Next
    INDEX
    Explanations

    periods of time

    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_56_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
     "]");
    0.43
    Мы
    0.42
     hand
    0.41
     손
    0.41
     HAND
    0.40
     Hand
    0.40
    手
    0.40
    ۾
    0.39
    Hand
    0.39
     পাতার
    0.39
    POSITIVE LOGITS
     years
    0.95
    Years
    0.89
    years
    0.83
     yrs
    0.81
     MANY
    0.80
     many
    0.79
    many
    0.77
     YEARS
    0.75
     Years
    0.75
     Many
    0.73
    Activations Density 0.001%

    No Known Activations