© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3534
    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_5_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
    Т
    0.64
    нє
    0.60
    М
    0.56
     striis
    0.55
     ゼ
    0.53
     فيها
    0.53
    Д
    0.53
    헨
    0.53
    Л
    0.52
     maestros
    0.52
    POSITIVE LOGITS
     explosive
    0.57
     colorful
    0.56
     dynamite
    0.56
     navigable
    0.55
    ו
    0.55
     larceny
    0.52
    ας
    0.52
     fabricating
    0.52
    audioType
    0.51
    ie
    0.51
    Activations Density 0.000%

    No Known Activations