© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258871
    Prev
    Next
    INDEX
    Explanations

    put hand in pocket

    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_10_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
     intermolecular
    0.91
     refle
    0.90
    uid
    0.89
    쉴
    0.86
     sodass
    0.83
     intervalles
    0.80
     Axes
    0.78
     কৌ
    0.77
    పరి
    0.77
    idis
    0.77
    POSITIVE LOGITS
     ottimo
    0.89
    M
    0.89
     ভিত্তিক
    0.87
     보고
    0.84
     دیگر
    0.84
     વિસ્ત
    0.84
    Ꭶ
    0.84
    hiqdev
    0.84
     Estudio
    0.83
     máte
    0.83
    Activations Density 0.000%

    No Known Activations