© 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. 3394
    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
    ói
    2.54
    ый
    2.47
    ata
    2.42
    ات
    2.39
    ów
    2.22
    ía
    2.21
    絽
    2.16
    h
    2.07
    ब्ल्यू
    2.06
     Chaque
    2.06
    POSITIVE LOGITS
    ductory
    2.45
    baka
    2.45
    ו
    2.35
     deposed
    2.29
    ется
    2.28
    scapes
    2.27
    spaces
    2.27
    সব
    2.26
    ings
    2.26
    вое
    2.24
    Activations Density 0.128%

    No Known Activations