© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 72
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     ∑
    1.94
    a
    1.94
    ve
    1.88
    g
    1.82
    ক
    1.77
    ⟨
    1.72
    aarr
    1.70
    𝒗
    1.70
    cele
    1.69
     kinks
    1.68
    POSITIVE LOGITS
    م
    2.58
    ان
    1.83
    an
    1.82
    driven
    1.73
     greatness
    1.70
    ью
    1.69
    िक
    1.68
    ные
    1.67
    gameOver
    1.66
    சால
    1.66
    Activations Density 0.044%

    No Known Activations