© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245569
    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_11_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
     communément
    1.42
    innerApiCalls
    1.28
     steric
    1.27
    篌
    1.24
    ческая
    1.22
     propi
    1.22
     molécules
    1.21
    féle
    1.21
     метров
    1.20
     doppia
    1.19
    POSITIVE LOGITS
    y
    1.36
    知らせ
    1.15
    yte
    1.10
    너
    1.07
    Inbox
    1.07
    ्स
    1.04
    ם
    1.02
    统一
    1.01
    ysis
    0.98
    中でも
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.