© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    over forty, monthly sessions

    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
    د
    2.46
    м
    2.12
    icación
    2.00
    т
    1.98
     Як
    1.94
     aş
    1.93
     éviter
    1.92
     які
    1.91
     unob
    1.88
    دان
    1.85
    POSITIVE LOGITS
    <bos>
    2.01
     (>
    1.99
    tones
    1.85
    剰
    1.84
     thể
    1.84
    ores
    1.82
    ría
    1.81
    ificates
    1.78
    >>>
    1.77
     века
    1.73
    Activations Density 0.049%

    No Known Activations