© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260905
    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
    usakan
    1.19
    ي
    1.17
    রুখ
    1.15
    ਾਂ
    1.15
    ायतों
    1.12
    reeks
    1.11
    ਿਕ
    1.11
    imiz
    1.10
    DateTime
    1.10
    কারী
    1.10
    POSITIVE LOGITS
     č
    1.20
     pry
    1.16
     bril
    1.14
     especially
    1.13
     heed
    1.12
     dyes
    1.10
     heels
    1.10
     sees
    1.10
     žád
    1.10
     padrões
    1.09
    Activations Density 0.000%

    No Known Activations