© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 56
    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_2_width_16k_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
    oretically
    0.19
    IAMS
    0.14
    zelfde
    0.14
    ️
    0.13
    обходимо
    0.13
    ations
    0.13
    luster
    0.13
     fussy
    0.12
    ordinary
    0.12
    скольку
    0.12
    POSITIVE LOGITS
    ᴘ
    0.17
    শ
    0.14
    joner
    0.14
    órios
    0.13
    ாதீர்கள்
    0.13
    scraper
    0.13
    ك
    0.13
     lesion
    0.13
    Excerpt
    0.13
    ʟ
    0.13
    Activations Density 0.045%

    No Known Activations