© 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. 5564
    Prev
    Next
    INDEX
    Explanations

    set property accessor

    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
    𝐬
    1.17
    𝐭
    0.95
    𝐥
    0.93
     cheers
    0.93
    䇝
    0.92
    𝐰
    0.91
    𝑤
    0.90
    +}
    0.88
    𝙨
    0.88
    +}$
    0.88
    POSITIVE LOGITS
    й
    0.88
    taker
    0.85
    ना
    0.83
     dikenal
    0.82
    től
    0.82
    ar
    0.77
    তে
    0.77
    йся
    0.77
    thing
    0.76
    ן
    0.74
    Activations Density 0.002%

    No Known Activations