© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    thespruce

    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
    oretically
    0.93
    сть
    0.86
     طريق
    0.81
    ка
    0.80
    是
    0.78
    el
    0.77
     xhr
    0.76
    <unused685>
    0.75
    ך
    0.74
    民间
    0.74
    POSITIVE LOGITS
     profesora
    0.80
    ein
    0.78
    ೇವೆ
    0.76
     tlač
    0.75
     sì
    0.75
     usk
    0.75
    ją
    0.74
    SEL
    0.74
    зной
    0.70
     aussch
    0.70
    Activations Density 0.003%

    No Known Activations