© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 198
    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_12_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
     päät
    0.25
     gase
    0.24
    รูป
    0.24
    尣
    0.23
     মুক্তিযোদ্ধ
    0.23
     dout
    0.23
     pitan
    0.23
    <unused2206>
    0.23
     nauk
    0.23
     ചിത്രം
    0.23
    POSITIVE LOGITS
    As
    0.27
    controllers
    0.25
    िंग
    0.24
    Along
    0.24
    Chord
    0.23
    Although
    0.23
    Con
    0.23
    Period
    0.23
    studies
    0.23
    El
    0.23
    Activations Density 0.518%

    No Known Activations