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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4481
    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
    ak
    0.37
    د
    0.36
    س
    0.35
     bothering
    0.33
    imiento
    0.32
     inhabited
    0.32
    ב
    0.32
    ңы
    0.32
    हार
    0.32
    态
    0.32
    POSITIVE LOGITS
     linewidth
    0.42
     tinggi
    0.42
    lt
    0.42
     statusCode
    0.41
     अबा
    0.38
    KAR
    0.38
     boundingRect
    0.38
    andin
    0.38
     Мы
    0.38
    inalg
    0.37
    Activations Density 0.122%

    No Known Activations