© 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. 3721
    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
    چه
    1.85
     airing
    1.74
    zuoye
    1.73
     धक्का
    1.70
     Таким
    1.66
    ısının
    1.64
    E
    1.63
    dealing
    1.62
     basal
    1.61
    sulfanyl
    1.60
    POSITIVE LOGITS
    𝑂
    1.90
    $-\
    1.82
    𝑒
    1.81
     również
    1.78
    いません
    1.66
    𝑃
    1.62
    あまり
    1.60
     liegt
    1.60
     weiterhin
    1.60
    𝓇
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.