© 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. 2945
    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
    ︎
    2.57
    ят
    2.52
    اء
    2.39
    样的
    2.36
    advisor
    2.31
    ুদ্র
    2.30
    ্ভব
    2.26
    스러운
    2.24
     "";
    2.24
    existent
    2.22
    POSITIVE LOGITS
    ను
    2.33
    ে
    2.26
    сь
    2.11
    กา
    2.09
    삼성
    2.01
     bersih
    2.00
    ly
    1.99
    エース
    1.95
    g
    1.94
    llan
    1.93
    Activations Density 0.039%

    No Known Activations