© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1896
    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_39_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
     Bord
    0.41
    replaceAll
    0.40
    bord
    0.39
     -(
    0.39
     retrato
    0.39
    涌
    0.39
    ética
    0.38
    lamak
    0.38
    ঙ্গি
    0.38
    ଲା
    0.37
    POSITIVE LOGITS
    虺
    0.48
    natures
    0.38
    Process
    0.37
     millet
    0.37
     happiness
    0.36
     Wilderness
    0.36
     filtered
    0.36
    buildSpec
    0.35
     what
    0.34
     Lindsey
    0.34
    Activations Density 0.000%

    No Known Activations