© 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. 258128
    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
     replacing
    1.39
     impeach
    1.38
     criminals
    1.36
     dieu
    1.33
    тории
    1.26
     taches
    1.24
     जवाब
    1.23
    ≌
    1.23
    🎢
    1.21
    ILIO
    1.20
    POSITIVE LOGITS
    et
    1.45
    л
    1.37
    fin
    1.06
    a
    1.02
    Divider
    1.01
    н
    1.01
    ت
    1.01
    zur
    1.01
    liter
    0.97
    েল
    0.97
    Activations Density 0.000%

    No Known Activations