© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259221
    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_10_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
    符
    1.24
     elasticity
    1.18
     scholarships
    1.13
    ಕಾರಿ
    1.13
    ≜
    1.11
     summand
    1.08
     pluck
    1.06
     odred
    1.05
     coined
    1.04
     pháp
    1.01
    POSITIVE LOGITS
    ب
    1.62
     geweld
    1.25
     завое
    1.22
    aventure
    1.19
    Fract
    1.15
    การ
    1.11
    스를
    1.11
    𝕒
    1.11
    ше
    1.10
    なった
    1.10
    Activations Density 0.000%

    No Known Activations