© 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. 8061
    Prev
    Next
    INDEX
    Explanations

    Key elements

    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
    ிறது
    1.16
    ো
    1.00
    िडेट
    0.93
     whipping
    0.91
    ر
    0.90
    ول
    0.89
    ضافة
    0.88
    isVideo
    0.86
    து
    0.86
    SQLALCHEMY
    0.84
    POSITIVE LOGITS
    itive
    0.85
    itäten
    0.81
    crime
    0.81
    Як
    0.78
    樯
    0.78
     clichés
    0.78
    ğun
    0.77
    más
    0.77
     desta
    0.75
    bons
    0.75
    Activations Density 0.072%

    No Known Activations