© 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. 5369
    Prev
    Next
    INDEX
    Explanations

    let math variable

    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
     simp
    1.08
    력
    1.08
    력을
    1.03
    յ
    1.03
    ть
    1.02
    ра
    0.97
     USO
    0.97
    %)
    0.96
    हमी
    0.96
    력이
    0.95
    POSITIVE LOGITS
     circumstance
    1.04
     boutons
    1.04
     isometry
    1.03
    mehr
    1.03
    ྜ
    1.03
    த்
    1.02
     platelets
    1.02
    eping
    1.01
    isière
    1.00
    ি
    0.99
    Activations Density 0.116%

    No Known Activations