© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5429
    Prev
    Next
    INDEX
    Explanations

    code structures and data types

    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
    z
    2.87
    ities
    2.71
     ð
    2.53
    次的
    2.40
     supérieur
    2.40
    ück
    2.38
    sortBy
    2.38
    alities
    2.36
     disparu
    2.34
     portant
    2.33
    POSITIVE LOGITS
    ا
    3.43
    𝙩
    3.26
    ্লাহ
    2.99
    𝙢
    2.95
    𝙣
    2.89
    ocht
    2.85
    𝙤
    2.84
    𝙡
    2.84
    я
    2.83
    𝙮
    2.82
    Activations Density 0.004%

    No Known Activations