© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256827
    Prev
    Next
    INDEX
    Explanations

    Bradberry, Paw Patrol, families, Wilson, Murray

    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_10_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
    Theorem
    0.32
     methods
    0.31
    Downtown
    0.30
    ClN
    0.30
     downtown
    0.30
    AsyncTask
    0.30
    Ƹ
    0.30
    ได้
    0.29
     fascinating
    0.29
    在日本
    0.29
    POSITIVE LOGITS
     agradecer
    0.43
     кух
    0.39
    eduanya
    0.38
    щены
    0.38
     iguales
    0.38
     pediat
    0.38
    acknow
    0.37
     семья
    0.37
    甜
    0.37
    ровали
    0.36
    Activations Density 0.001%

    No Known Activations