© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173962
    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
    та
    0.58
    ハ
    0.52
    h
    0.51
    的三
    0.49
    のための
    0.49
    تن
    0.48
    d
    0.47
    ))){
    0.47
    to
    0.47
    تنا
    0.47
    POSITIVE LOGITS
     astrophys
    0.51
     incumbent
    0.48
     eigenvalue
    0.47
     acrylic
    0.45
    ĝ
    0.45
     isoform
    0.45
     entryway
    0.44
     autonomic
    0.44
     menghubungi
    0.44
     implants
    0.43
    Activations Density 0.000%

    No Known Activations