© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66486
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    marginTop
    0.43
    افل
    0.43
    recen
    0.42
     комплек
    0.40
     комплекс
    0.40
     Yum
    0.39
    窜
    0.38
     margen
    0.38
    掏
    0.38
     दंपति
    0.38
    POSITIVE LOGITS
     reduction
    0.46
    Material
    0.46
     Terra
    0.46
    Reducer
    0.46
    ﮗ
    0.45
     material
    0.44
     Vetter
    0.44
     reductions
    0.44
     redu
    0.42
     papp
    0.42
    Activations Density 0.000%

    No Known Activations