Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15200
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_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
     በመ
    0.77
    गेन
    0.77
     원
    0.70
    Mobile
    0.69
    ByName
    0.69
     პირ
    0.67
    昻
    0.66
     반
    0.66
    MOBILE
    0.66
     环境
    0.65
    POSITIVE LOGITS
     conducting
    0.71
     Otra
    0.70
     tried
    0.70
     anderem
    0.70
     outra
    0.68
    或其他
    0.68
     another
    0.67
    带领
    0.67
     conduction
    0.65
     ru
    0.64
    Activations Density 0.013%

    No Known Activations