© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3517
    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_5_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
    н
    1.64
    a
    1.56
    ン
    1.52
     foco
    1.52
     cierto
    1.50
    keme
    1.49
    르
    1.47
    
    1.44
     Чтобы
    1.43
    うちに
    1.42
    POSITIVE LOGITS
    يح
    2.01
    ğmen
    1.98
    दायक
    1.91
    Hoch
    1.90
    stricken
    1.85
    yuk
    1.80
    PSY
    1.76
    ஸ்
    1.74
    সি
    1.73
    penas
    1.73
    Activations Density 0.000%

    No Known Activations