© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    JSON structure

    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
    ка
    2.72
    员
    2.37
     помнить
    2.36
    𝘁
    2.34
    𝗳
    2.33
    𝘂
    2.25
    将
    2.24
     întâm
    2.23
    ى
    2.19
    től
    2.18
    POSITIVE LOGITS
    ました
    3.12
    𝐧
    3.02
    𝐫
    2.95
    𝐝
    2.91
    𝖘
    2.74
    𝐬
    2.64
    𝐥
    2.54
    𝐍
    2.44
    यान
    2.36
    nesday
    2.35
    Activations Density 0.094%

    No Known Activations