© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2636
    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
    ро
    2.56
    ы
    2.48
    unun
    2.33
    ある
    2.32
    ခြေ
    2.31
    軸
    2.22
     achieve
    2.21
    매
    2.21
     gian
    2.19
     ряд
    2.19
    POSITIVE LOGITS
    c
    2.61
    GUILayout
    2.59
    cY
    2.56
    yard
    2.45
    a
    2.37
    iť
    2.34
    cD
    2.34
    it
    2.31
    yards
    2.29
    rare
    2.28
    Activations Density 0.012%

    No Known Activations