© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150742
    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_18_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
    爫
    0.50
    owneri
    0.48
    >∕
    0.48
    Idea
    0.47
     correttamente
    0.46
    菘
    0.46
    ショー
    0.45
    >′
    0.45
    墘
    0.45
    ONE
    0.44
    POSITIVE LOGITS
    count
    0.47
    reel
    0.46
    lars
    0.45
    -
    0.42
    ront
    0.42
     out
    0.42
    belt
    0.41
    fabric
    0.40
    affection
    0.40
    멍
    0.39
    Activations Density 0.000%

    No Known Activations