© 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. 5256
    Prev
    Next
    INDEX
    Explanations

    SQL REFERENCES keyword

    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
     불구하고
    2.21
    ंगाई
    2.20
    ো
    2.13
    setColor
    2.05
    hagen
    2.00
    ളാ
    1.96
     urin
    1.96
     তবে
    1.96
    ్య
    1.95
    倜
    1.95
    POSITIVE LOGITS
    ли
    3.05
    आई
    2.83
    🅻
    2.49
    د
    2.46
    er
    2.36
     Contrary
    2.35
    Ли
    2.34
    ique
    2.29
    NL
    2.29
    ер
    2.27
    Activations Density 0.001%

    No Known Activations