© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    break down what

    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
    ಯಲ್ಲಿ
    1.56
    s
    1.42
    ν
    1.41
    кла
    1.37
    三种
    1.35
    به
    1.33
    sia
    1.32
     importantly
    1.31
    高
    1.30
     inconsistencies
    1.29
    POSITIVE LOGITS
    ارة
    1.39
    onnés
    1.34
    <bos>
    1.33
    WEBPACK
    1.32
    as
    1.23
    ен
    1.22
    еш
    1.22
    ام
    1.22
    ̀u
    1.19
    ที่สุด
    1.17
    Activations Density 0.080%

    No Known Activations