© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    patents and technologies

    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
    ن
    2.87
     раствора
    2.73
    ра
    2.70
    وين
    2.52
     проведе
    2.42
     troops
    2.37
     unwilling
    2.31
    রিষ্ঠ
    2.31
    ಕ್ರ
    2.29
    یر
    2.29
    POSITIVE LOGITS
     conjunction
    2.95
    धर्म
    2.49
     ahol
    2.46
    त
    2.44
    ্ন
    2.37
    ished
    2.23
     razy
    2.15
    vamo
    2.14
     lieu
    2.14
     been
    2.14
    Activations Density 0.017%

    No Known Activations