© 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. 5419
    Prev
    Next
    INDEX
    Explanations

    calculate, find, update, merge

    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
    ts
    0.65
     zejména
    0.63
    ل
    0.60
     elett
    0.60
    conj
    0.58
    también
    0.57
    ல்லாம்
    0.57
    つ
    0.56
    tai
    0.56
    Ć
    0.56
    POSITIVE LOGITS
    atakse
    0.63
    সময়
    0.63
    են
    0.63
    𝗿
    0.63
    𝗳
    0.63
    անդ
    0.62
     존재하는
    0.62
    ίναι
    0.61
    諄
    0.61
     помощью
    0.60
    Activations Density 0.131%

    No Known Activations