© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2046
    Prev
    Next
    INDEX
    Explanations

    python `time` and `json`

    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_39_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
     resorption
    0.34
    삭제
    0.30
    IBRARY
    0.30
    蓉
    0.30
    Issledovatel
    0.29
    蘼
    0.29
    бліоте
    0.29
    棰
    0.29
    蓮
    0.29
     captioned
    0.29
    POSITIVE LOGITS
    entr
    0.33
    dict
    0.31
    ring
    0.31
     awe
    0.30
     spades
    0.30
    Ross
    0.29
     faces
    0.29
    殁
    0.29
     gin
    0.29
     dice
    0.28
    Activations Density 0.029%

    No Known Activations