© 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. 8498
    Prev
    Next
    INDEX
    Explanations

    handling exceptions

    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
    语
    2.15
     eléctrica
    2.14
    ಗೊಳ್ಳ
    2.11
     همین
    2.04
     mixto
    2.02
    ността
    1.97
    器
    1.95
     homestead
    1.93
    ยนต์
    1.93
     titulado
    1.93
    POSITIVE LOGITS
    ب
    2.69
    вими
    2.60
    ri
    2.43
    墅
    2.38
    re
    2.33
    leqslant
    2.32
    ൾ
    2.31
    h
    2.28
    letzt
    2.27
    ar
    2.24
    Activations Density 0.006%

    No Known Activations