© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256390
    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
    Negative Logits
     eigenstates
    1.49
    IFIER
    1.45
     exaggerate
    1.43
     actuators
    1.32
     comboBox
    1.31
    zynarod
    1.29
     invertebrates
    1.28
    >}
    1.27
    韬
    1.26
     Azer
    1.26
    POSITIVE LOGITS
    う
    1.21
     উহার
    1.04
     когда
    1.01
     fire
    0.99
    દ્
    0.99
     \
    0.99
    renc
    0.97
     conflicto
    0.95
     involved
    0.94
    enza
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.