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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3908
    Prev
    Next
    INDEX
    Explanations

    lint configuration

    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_40_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
    SPRAY
    0.32
     SUBSCRIBE
    0.32
     inked
    0.31
    䊂
    0.31
     SUNY
    0.30
    γκε
    0.29
    ৯
    0.29
    তত্ব
    0.29
    áctica
    0.29
    ᱲ
    0.29
    POSITIVE LOGITS
     Esp
    0.31
    大师
    0.30
     bracket
    0.29
     scavenging
    0.29
     ഓ
    0.29
    Bracket
    0.29
     Braga
    0.28
    动物
    0.28
     config
    0.27
    万円
    0.27
    Activations Density 0.002%

    No Known Activations