© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3167
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     tangents
    2.86
     النظام
    2.66
     زمانی
    2.59
     بیٹھ
    2.56
    ни
    2.56
     якія
    2.56
     pasos
    2.53
    칙
    2.52
     расстоя
    2.52
    ஔ
    2.50
    POSITIVE LOGITS
    ب
    3.29
    nex
    2.72
    overset
    2.71
    ব্য
    2.71
    ことができます
    2.70
    nilai
    2.70
     vitro
    2.69
    ︎
    2.66
    '-
    2.62
    ব
    2.56
    Activations Density 0.062%

    No Known Activations