© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62961
    Prev
    Next
    INDEX
    Explanations

    code declarations and documentation

    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_41_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
    请求
    0.42
     batches
    0.41
    REQUEST
    0.40
     grains
    0.40
    抂
    0.38
    ʇ
    0.37
    ദ്യ
    0.36
    Nab
    0.36
    動
    0.35
    キャッシュ
    0.34
    POSITIVE LOGITS
     Grec
    0.42
    讃
    0.40
     Ges
    0.39
    Farland
    0.39
     ट्रांसजेंडर
    0.38
     Blend
    0.38
     Productivity
    0.37
    ienz
    0.37
     Gardening
    0.37
    enzie
    0.37
    Activations Density 0.000%

    No Known Activations