© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130132
    Prev
    Next
    INDEX
    Explanations

    optim, nn

    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_25_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
     ח
    0.43
     식
    0.38
     주변
    0.38
     등이
    0.38
     ჰ
    0.37
     버
    0.37
    ห
    0.37
    기가
    0.37
     내용
    0.37
     자체가
    0.36
    POSITIVE LOGITS
    形で
    0.37
     apaixon
    0.37
     selling
    0.36
     Invest
    0.35
     publication
    0.35
     GestureDetector
    0.35
     invested
    0.35
     Darryl
    0.35
    ote
    0.34
     publi
    0.34
    Activations Density 0.000%

    No Known Activations