© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3447
    Prev
    Next
    INDEX
    Explanations

    javascript code 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_5_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
    igned
    0.45
    œil
    0.44
    getattr
    0.40
    ogon
    0.37
    ∑
    0.37
    꼰
    0.37
    इसके
    0.36
    다른
    0.36
     الض
    0.36
    적으로
    0.36
    POSITIVE LOGITS
    ت
    0.50
    های
    0.48
    েরা
    0.43
    今日は
    0.42
    itats
    0.42
    ش
    0.42
    ствии
    0.42
    లు
    0.41
     deportivas
    0.41
    рів
    0.41
    Activations Density 0.055%

    No Known Activations