© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3001
    Prev
    Next
    INDEX
    Explanations

    nature of

    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_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
    াগর
    1.94
    at
    1.91
    ^{
    1.88
    laughs
    1.86
    isset
    1.85
    u
    1.84
    स्पति
    1.83
    \]
    1.82
    ä
    1.81
    '$
    1.80
    POSITIVE LOGITS
     गंभीरता
    2.10
    ни
    2.07
    ו
    2.02
    措置
    1.96
    ۰
    1.93
    ठमाड
    1.90
     truth
    1.89
    ठमाडौं
    1.88
     asl
    1.87
    鮒
    1.87
    Activations Density 0.041%

    No Known Activations