© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5453
    Prev
    Next
    INDEX
    Explanations

    Force, OS, Service

    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
    i
    2.64
    і
    2.62
    ल्पनिक
    2.55
    ي
    2.38
     dever
    2.38
    దే
    2.36
    srv
    2.30
    詞
    2.28
    ﺭ
    2.27
    one
    2.18
    POSITIVE LOGITS
    cin
    3.04
     equalization
    2.91
    ocurrency
    2.59
    shire
    2.53
     heed
    2.47
     esperti
    2.45
     chevaux
    2.43
     chance
    2.39
     Etern
    2.36
     elbows
    2.33
    Activations Density 0.008%

    No Known Activations