© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    summarizing tables

    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
    橥
    0.64
     ce
    0.60
     начала
    0.56
    roidism
    0.56
    自治区
    0.55
    เป็น
    0.55
     खड़े
    0.52
    ær
    0.52
     MPR
    0.52
     fod
    0.51
    POSITIVE LOGITS
    𝑯
    0.83
    jogador
    0.80
    ुअल
    0.80
    ശാസ്ത്ര
    0.77
    ˆ‚
    0.77
    माइंडर
    0.77
     SQLException
    0.77
    লাষ
    0.74
    equalsIgnoreCase
    0.74
    lN
    0.73
    Activations Density 0.081%

    No Known Activations