© 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. 130629
    Prev
    Next
    INDEX
    Explanations

    lines and separators

    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
    etting
    0.13
    awie
    0.12
    ahlen
    0.12
     requester
    0.12
    过
    0.12
     fgets
    0.12
    演唱
    0.12
     fileobj
    0.11
    ERA
    0.11
     부탁
    0.11
    POSITIVE LOGITS
     ক্রিম
    0.16
    ø
    0.13
     territo
    0.13
     Geography
    0.13
    शहर
    0.12
    hotel
    0.12
    editorial
    0.12
     Lyons
    0.12
     Gilroy
    0.12
    Geography
    0.12
    Activations Density 0.001%

    No Known Activations