© 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. 7225
    Prev
    Next
    INDEX
    Explanations

    pay attention, start small

    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
     concerted
    0.38
     подготовлено
    0.37
    巧妙
    0.35
    смотрим
    0.33
    checkFor
    0.33
    पहली
    0.32
    꿋
    0.32
     prepar
    0.32
    푞
    0.32
     Prepare
    0.31
    POSITIVE LOGITS
    Someone
    0.35
     نفسه
    0.32
     নিষেধ
    0.32
    Rice
    0.32
     ਮੁ
    0.31
     catwalk
    0.31
    痰
    0.30
     anemia
    0.30
    IMENTS
    0.30
    sun
    0.29
    Activations Density 0.047%

    No Known Activations