© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3454
    Prev
    Next
    INDEX
    Explanations

    YouTube videos

    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
    n
    0.79
    в
    0.76
    ส์
    0.73
    r
    0.73
    તર
    0.72
    stained
    0.71
    means
    0.69
    Rewrite
    0.68
    ]]
    0.68
    ду
    0.67
    POSITIVE LOGITS
     redundancies
    0.80
     wenige
    0.75
    ɴ
    0.72
    тою
    0.70
    ي
    0.70
    ে
    0.68
    elajaran
    0.68
    哝
    0.67
    чках
    0.65
    pping
    0.65
    Activations Density 0.011%

    No Known Activations