© 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. 7977
    Prev
    Next
    INDEX
    Explanations

    anticipatory bail

    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
    يز
    2.75
    こんにちは
    2.63
     wonder
    2.40
    다른
    2.38
    नंतर
    2.35
    Ꮃ
    2.29
    ть
    2.28
     tính
    2.24
     inconvenience
    2.21
    ні
    2.20
    POSITIVE LOGITS
    ă
    2.72
    व
    2.41
     прошу
    2.40
    ামীর
    2.35
    лу
    2.29
     ряда
    2.28
    agiri
    2.22
     actionMode
    2.22
     скажу
    2.21
    ज
    2.20
    Activations Density 0.034%

    No Known Activations