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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8201
    Prev
    Next
    INDEX
    Explanations

    fire

    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
    an
    1.16
    سا
    1.08
    ০
    1.07
    ल
    1.06
    ually
    0.90
    गौर
    0.90
    م
    0.89
    ১
    0.88
    のは
    0.87
    findings
    0.87
    POSITIVE LOGITS
     Faz
    1.00
    ດ
    0.97
     мере
    0.95
     FAX
    0.92
     upang
    0.91
    ண்ட்
    0.90
    с
    0.89
     Ditto
    0.88
    OF
    0.88
     vista
    0.87
    Activations Density 0.003%

    No Known Activations