© 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. 257651
    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
    ocious
    1.34
    로
    1.33
    <0x0C>
    1.27
    ات
    1.27
    مین
    1.24
     पीस
    1.21
    যজ্ঞ
    1.20
     arrondies
    1.20
     CONSEQUENTIAL
    1.19
    elves
    1.19
    POSITIVE LOGITS
     وق
    1.17
     accompanying
    1.15
    lí
    1.06
    n
    1.06
    re
    1.02
    崢
    1.01
     certiorari
    1.01
    कै
    1.00
    แด
    0.99
    𝑟
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.