© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    before taking action

    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
    य
    2.02
    此之外
    1.97
    यों
    1.95
    т
    1.87
    های
    1.85
     ovary
    1.84
     mát
    1.83
     conjunta
    1.82
    ス
    1.78
     kada
    1.78
    POSITIVE LOGITS
     dawn
    2.24
     adjour
    2.18
     sunrise
    2.13
     sempat
    2.09
    েল
    2.01
    יא
    1.97
    ный
    1.90
    ভাগে
    1.87
     лицом
    1.83
     وبعد
    1.82
    Activations Density 0.050%

    No Known Activations