© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56876
    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_11_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
    ર્ટ
    0.48
    azas
    0.48
     nariz
    0.46
    ăz
    0.45
    ળ
    0.45
    र्ड
    0.44
     zaključ
    0.44
    िक्स
    0.43
    ಸಿ
    0.43
    dimensionality
    0.43
    POSITIVE LOGITS
     Institute
    0.46
    Russell
    0.45
     Resource
    0.44
     буль
    0.44
     Value
    0.43
     대
    0.42
     An
    0.42
     compiling
    0.42
    筤
    0.41
    Institute
    0.41
    Activations Density 0.000%

    No Known Activations