© 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. 5357
    Prev
    Next
    INDEX
    Explanations

    legacy","nursing","Roller","food","agriculture","sanitation","medicine"

    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
    Disha
    1.24
    鸯
    1.22
    THEOREM
    1.18
    explode
    1.15
     delimiters
    1.13
     smack
    1.13
     precincts
    1.10
    ાડ
    1.10
    숱
    1.09
     quoi
    1.08
    POSITIVE LOGITS
    त
    1.64
    तत्
    1.15
    دخل
    1.02
    ip
    1.01
    amt
    0.99
    لكتر
    0.99
    ity
    0.98
    ère
    0.97
    eniendo
    0.97
    д
    0.96
    Activations Density 0.000%

    No Known Activations