© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175136
    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_20_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
     mitochond
    0.62
     oxidizing
    0.61
     photosynthesis
    0.59
     минера
    0.59
     chloroplast
    0.57
    <unused667>
    0.57
    graphHead
    0.57
    𝚣
    0.56
     bitOp
    0.55
     несмотря
    0.55
    POSITIVE LOGITS
    I
    0.52
    행
    0.49
    ING
    0.46
    AN
    0.45
    Ill
    0.45
    ano
    0.44
    re
    0.44
    ier
    0.44
    1
    0.44
    Martin
    0.43
    Activations Density 0.000%

    No Known Activations