© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3725
    Prev
    Next
    INDEX
    Explanations

    Foreign words and non-English text

    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_5_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
    as
    2.04
    it
    1.71
    ̇
    1.59
    و
    1.46
    in
    1.45
    ু
    1.42
    ového
    1.42
     suppose
    1.41
    akta
    1.40
    ぷ
    1.39
    POSITIVE LOGITS
     সুতরাং
    1.67
     оби
    1.62
     plufieurs
    1.50
     mistura
    1.45
     Nxa
    1.45
    лизова
    1.43
     فات
    1.42
    जीलैंड
    1.40
     inflicted
    1.38
     précéd
    1.37
    Activations Density 0.000%

    No Known Activations