© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5386
    Prev
    Next
    INDEX
    Explanations

    Dota 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ీ
    3.23
    ر
    3.20
    
    2.52
     faute
    2.46
    ра
    2.45
     toga
    2.30
     dass
    2.30
    şi
    2.24
    ज
    2.24
     dus
    2.21
    POSITIVE LOGITS
    tains
    2.79
    ❒
    2.68
     суще
    2.64
     denominator
    2.59
    tuples
    2.58
     সেক্ষেত্রে
    2.53
    aný
    2.51
    ம்பரிய
    2.50
     sadr
    2.50
     tengamos
    2.50
    Activations Density 0.011%

    No Known Activations