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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 246103
    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_11_width_262k_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
    inde
    1.09
    ice
    1.09
    ion
    1.06
     lomba
    1.04
    is
    1.04
    ½
    1.03
    re
    1.02
     tal
    1.01
     tais
    1.00
    multiply
    0.99
    POSITIVE LOGITS
    ن
    1.20
     marvell
    1.19
     Чтобы
    1.19
    க்ஸாண்ட
    1.18
     труб
    1.17
    าะ
    1.16
     Detalles
    1.16
    ⱨ
    1.15
     എന്ന
    1.14
     clapping
    1.13
    Activations Density 0.000%

    No Known Activations