© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13965
    Prev
    Next
    INDEX
    Explanations

    minute (0-59), second (0-59)

    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_40_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
    tpl
    0.35
    솝
    0.35
    障害
    0.34
    abhave
    0.34
     பதில
    0.32
    ച്ചത്
    0.32
    大切な
    0.32
    楠
    0.32
    antina
    0.32
    Ⓘ
    0.31
    POSITIVE LOGITS
     Add
    0.39
     ken
    0.36
     union
    0.34
     filled
    0.34
     Joshua
    0.33
     {{-
    0.33
     Kenney
    0.33
    Add
    0.32
     Pr
    0.32
     Union
    0.32
    Activations Density 0.002%

    No Known Activations