© 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. 258715
    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
     lacus
    1.14
    aní
    1.09
    ᴄ
    1.07
     آنان
    1.06
     banished
    1.05
    unable
    1.04
     oppressive
    1.03
     blissful
    1.03
     distorted
    1.03
    abuse
    1.01
    POSITIVE LOGITS
     Hypothesis
    0.92
     Macron
    0.92
     frais
    0.85
     Banker
    0.83
     Comme
    0.81
     DMG
    0.81
     thinkers
    0.80
    汎
    0.80
     Trench
    0.80
    Tucker
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.