© 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. 5170
    Prev
    Next
    INDEX
    Explanations

    C# code statements

    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
    ق
    2.91
    諧
    2.86
    eyeglasses
    2.46
    ோ
    2.46
    ﺰ
    2.46
    ब्ल्यू
    2.45
    स्पति
    2.39
    isées
    2.38
    पी
    2.37
     halfway
    2.31
    POSITIVE LOGITS
     \%\
    2.63
    curr
    2.61
     ćete
    2.40
     việc
    2.36
    ━━
    2.36
    matic
    2.33
    Leftrightarrow
    2.28
     Việc
    2.27
    drawable
    2.26
    nail
    2.25
    Activations Density 0.000%

    No Known Activations