© 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
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130657
    Prev
    Next
    INDEX
    Explanations

    restaurants

    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
     Mic
    0.31
    inuation
    0.30
     Gre
    0.29
    Swap
    0.27
    業者
    0.27
     Krause
    0.27
    Installer
    0.27
    贪
    0.26
     X
    0.26
     Grease
    0.25
    POSITIVE LOGITS
     ଭ
    0.29
     decomposed
    0.29
    ન્મ
    0.29
     tecnológica
    0.29
    ibilités
    0.28
     peculi
    0.28
    няют
    0.28
    ۂ
    0.27
     specialised
    0.27
     полный
    0.27
    Activations Density 0.002%

    No Known Activations