© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253774
    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_56_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
    トップ
    0.43
     Top
    0.42
     μ
    0.39
     Chlor
    0.39
     Ker
    0.38
     EXEMPLARY
    0.37
    top
    0.37
    Top
    0.37
     Speech
    0.37
     chlor
    0.36
    POSITIVE LOGITS
     rock
    0.92
    rock
    0.77
    Rock
    0.68
     Rock
    0.60
     ROCK
    0.59
    ROCK
    0.58
     рок
    0.57
    岩
    0.55
     rocked
    0.54
     rocker
    0.50
    Activations Density 0.000%

    No Known Activations