© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165261
    Prev
    Next
    INDEX
    Explanations

    this one

    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_13_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
     چاپ
    0.49
    寒
    0.49
     Е
    0.46
    Labour
    0.46
    Languages
    0.46
     alumnos
    0.46
     Pagination
    0.45
     О
    0.44
    History
    0.44
    Travel
    0.43
    POSITIVE LOGITS
    तः
    0.46
     ост
    0.45
    𒁾
    0.45
     Aman
    0.43
     dem
    0.43
     grinder
    0.43
    עם
    0.43
    ঝে
    0.42
    𝐠
    0.42
    ggbb
    0.42
    Activations Density 0.000%

    No Known Activations