© 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. 257417
    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
    ूहिक
    1.24
     dissipative
    1.21
     ambiguity
    1.19
    谑
    1.18
     এদিকে
    1.17
    lewati
    1.14
    ñado
    1.10
    <unused321>
    1.10
    ellschaft
    1.09
     sucesión
    1.09
    POSITIVE LOGITS
    ми
    1.26
    СР
    1.09
     оста
    1.08
    த்
    1.07
     الغير
    1.06
    ти
    0.98
    હ
    0.97
    тип
    0.97
    GPA
    0.97
    陉
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.