© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155279
    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_60_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
     Pry
    0.38
     Bowers
    0.38
    Herbert
    0.37
    ্নে
    0.37
     Peirce
    0.36
    때
    0.36
     Truman
    0.35
    smt
    0.34
     Whitaker
    0.34
     Merritt
    0.34
    POSITIVE LOGITS
    ma
    0.46
    am
    0.44
    ан
    0.43
    ал
    0.41
    ilerini
    0.41
    aa
    0.41
    im
    0.41
    asi
    0.40
    hattisgarh
    0.40
     "**
    0.39
    Activations Density 0.000%

    No Known Activations