© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258589
    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
    ת
    1.29
    לים
    1.22
    bouw
    1.18
    erin
    1.18
     అది
    1.15
    ου
    1.11
    olar
    1.07
    ору
    1.06
    קד
    1.04
    চিত্রে
    1.03
    POSITIVE LOGITS
    )">
    1.33
    ங்கிணை
    1.21
    নি
    1.15
    )_
    1.14
    )})
    1.14
    дцать
    1.13
     funkc
    1.10
     Surreal
    1.09
     excer
    1.05
    łeś
    1.04
    Activations Density 0.000%

    No Known Activations