© 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. 5126
    Prev
    Next
    INDEX
    Explanations

    Beatrix Potter illustrations

    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
    ра
    2.73
    ад
    2.16
    ॅमिली
    2.08
     useless
    2.03
     Behold
    2.02
    الم
    1.97
    व
    1.95
    𝐩
    1.94
    handed
    1.93
     Begriff
    1.92
    POSITIVE LOGITS
    л
    2.52
    婿
    2.19
    𝗮
    2.16
    incare
    2.03
    此之外
    2.01
    仅仅
    2.00
    c
    1.99
    𝗛
    1.98
    娲
    1.98
     deter
    1.98
    Activations Density 0.012%

    No Known Activations