© 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. 257870
    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
    sgál
    1.32
    खार
    1.31
     עס
    1.30
    jší
    1.26
    -------*/
    1.21
     иң
    1.19
    माणे
    1.17
    ρικ
    1.14
    ɗ
    1.13
    curity
    1.13
    POSITIVE LOGITS
     sportsmen
    1.02
     cuál
    0.98
     wrench
    0.98
     cylinder
    0.98
    零部件
    0.98
     recorrido
    0.95
     accedi
    0.94
    Attendee
    0.92
     personnelle
    0.92
    মন্ত্র
    0.91
    Activations Density 0.000%

    No Known Activations