© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    notebook and laptop computing devices

    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
    ك
    3.17
    нение
    2.74
     aulas
    2.71
     stave
    2.70
    у
    2.68
     voilà
    2.67
    তা
    2.61
     fois
    2.59
    nze
    2.58
     respecto
    2.56
    POSITIVE LOGITS
    면
    2.51
     despatched
    2.46
     parasite
    2.45
     hood
    2.38
    या
    2.38
     doom
    2.38
     topologically
    2.36
    or
    2.32
     Perfectly
    2.30
    ल
    2.30
    Activations Density 0.013%

    No Known Activations