© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260409
    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_10_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
     passages
    1.10
    ፤
    1.10
     сериа
    1.08
    ຳ
    1.07
     Botanic
    1.06
     липня
    1.06
     soups
    1.05
    enzyme
    1.02
     sekaligus
    1.02
     ч
    1.01
    POSITIVE LOGITS
     hatt
    1.28
    رة
    1.18
    ்ப
    1.12
     Bedürfnisse
    1.11
     wund
    1.10
    烁
    1.07
     Skip
    1.07
    kert
    1.06
    tke
    1.05
    e
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.