© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    ORDER BY clause

    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
    ن
    0.88
     jok
    0.71
    selves
    0.69
    Dancing
    0.65
    ~/
    0.65
    ্ম
    0.65
    être
    0.64
    unlike
    0.64
    r
    0.63
    ⁇
    0.61
    POSITIVE LOGITS
    ्स
    0.97
    س
    0.87
    ació
    0.85
    ﺪ
    0.78
    কাল
    0.76
     tajem
    0.75
     abbia
    0.73
    getY
    0.72
     competente
    0.72
    onload
    0.71
    Activations Density 0.004%

    No Known Activations