© 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. 260904
    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
    t
    1.58
    timestamp
    1.48
    greek
    1.43
    dato
    1.43
    giveness
    1.40
    tica
    1.39
    zynarod
    1.31
    垨
    1.30
    tire
    1.30
    dynamics
    1.30
    POSITIVE LOGITS
    л
    1.20
    אם
    1.17
    ので
    1.13
     variété
    1.09
     mère
    1.00
     simplic
    0.99
     sta
    0.99
     tra
    0.99
     зрения
    0.97
     tersedia
    0.96
    Activations Density 0.000%

    No Known Activations