© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198262
    Prev
    Next
    INDEX
    Explanations

    units of time duration

    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_9_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
    ↵↵
    0.27
    ū
    0.26
    we
    0.26
    p
    0.26
    ש
    0.25
    pm
    0.25
     d
    0.25
    td
    0.23
    until
    0.23
    INTRODUCTION
    0.23
    POSITIVE LOGITS
    ről
    0.34
    ే
    0.34
    т
    0.31
     habitudes
    0.31
    on
    0.31
     dyads
    0.30
     discret
    0.30
    ת
    0.30
    ed
    0.30
    ле
    0.30
    Activations Density 0.002%

    No Known Activations