© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256671
    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
    ynchronous
    0.96
    )$.
    0.95
     c
    0.93
    ogeneous
    0.93
    Ν
    0.92
    ogenous
    0.89
    ційних
    0.89
    들이
    0.87
     अग्
    0.85
    navigationItem
    0.84
    POSITIVE LOGITS
    poder
    1.52
    кина
    1.38
     Oman
    1.38
     muffins
    1.37
     árboles
    1.36
     gestures
    1.34
     alder
    1.34
     símbolos
    1.34
    𝓂
    1.32
     arrondies
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.