© 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. 5493
    Prev
    Next
    INDEX
    Explanations

    http://localhost:3000

    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
    ठे
    2.81
    يك
    2.80
     Başkan
    2.78
     dese
    2.60
    曾
    2.50
    숫
    2.49
    টা
    2.46
    ната
    2.44
    ი
    2.43
    뎐
    2.41
    POSITIVE LOGITS
    rd
    3.23
     dàng
    2.84
    fourths
    2.79
    quarters
    2.75
    NotEmpty
    2.64
    дцать
    2.63
    terase
    2.62
    te
    2.56
     cheers
    2.50
    其
    2.49
    Activations Density 0.008%

    No Known Activations