© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 338
    Prev
    Next
    INDEX
    Explanations

    hello world

    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_38_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
    䢙
    0.41
    inded
    0.37
    Substituting
    0.36
     кров
    0.35
     बंगाल
    0.35
     `<=
    0.35
     गलती
    0.35
    㐬
    0.35
    డ్‌
    0.34
    呟
    0.34
    POSITIVE LOGITS
     skates
    0.44
     poth
    0.42
     skate
    0.41
    munk
    0.40
    boss
    0.40
    涉
    0.39
     skating
    0.39
     skaters
    0.38
    rasında
    0.38
    stove
    0.38
    Activations Density 0.047%

    No Known Activations