© 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. 260022
    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
    hilangan
    1.37
    紊
    1.29
    ants
    1.25
    ፡፡
    1.25
    TY
    1.17
    geht
    1.15
     mengetahui
    1.14
    அல்லாஹ்
    1.13
    لاة
    1.12
    जैसा
    1.10
    POSITIVE LOGITS
    تج
    1.17
    s
    1.10
    t
    1.07
    signup
    1.07
    क्व
    1.06
    م
    1.06
    kPa
    1.05
    Export
    1.04
    夻
    1.02
    客观
    1.01
    Activations Density 0.000%

    No Known Activations