© 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. 5229
    Prev
    Next
    INDEX
    Explanations

    cuda programming

    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
    ments
    2.75
    𝐝
    2.72
    𝐢
    2.64
    s
    2.55
    ด์
    2.51
    𝐞
    2.46
    ان
    2.44
    𝐚
    2.35
    🥯
    2.32
     ose
    2.32
    POSITIVE LOGITS
    ባድ
    2.20
    й
    2.06
    おそらく
    2.04
    два
    1.96
     endere
    1.95
    қа
    1.94
    деся
    1.88
     extol
    1.86
     entsch
    1.86
    ЦИ
    1.83
    Activations Density 0.001%

    No Known Activations