© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     aut
    0.48
     cie
    0.45
     propose
    0.43
     prendere
    0.42
     doi
    0.40
     ne
    0.39
     est
    0.39
     ­
    0.39
     bour
    0.39
     Comm
    0.37
    POSITIVE LOGITS
     হইলেই
    0.42
    ネル
    0.37
    住了
    0.37
    ดัง
    0.36
    CLM
    0.34
    ตัน
    0.33
    StudentNo
    0.33
    َة
    0.33
    actionMode
    0.33
    webElementGuid
    0.33
    Activations Density 0.000%

    No Known Activations