© 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. 3300
    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
     annat
    1.41
    toa
    1.40
    నా
    1.37
    üedad
    1.36
    ﺢ
    1.33
    t
    1.31
     educativas
    1.29
    toare
    1.27
     Católica
    1.27
     ರಿಂದ
    1.27
    POSITIVE LOGITS
    고
    1.30
    主义
    1.28
     fateful
    1.23
     postage
    1.23
    ال
    1.21
    ногда
    1.21
     ưu
    1.19
    \,\
    1.16
     పాటు
    1.14
    й
    1.14
    Activations Density 0.007%

    No Known Activations