© 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. 258977
    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
    town
    1.11
    ia
    1.11
    us
    1.09
     mamy
    1.05
    ንሽ
    1.02
     Ceci
    1.00
    个
    0.98
    usammen
    0.98
    ovat
    0.98
     foi
    0.95
    POSITIVE LOGITS
    Probability
    1.42
     GSH
    1.36
    SINGLE
    1.31
    CHRIST
    1.30
    куляр
    1.27
    ҳи
    1.26
    bokeh
    1.26
    פו
    1.24
    跹
    1.24
    Боль
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.