© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215843
    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_50_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
     Webster
    0.65
    Webster
    0.60
     Liverpool
    0.45
     Rochester
    0.40
     Stam
    0.39
     справед
    0.39
    可
    0.39
     रिश्
    0.39
     Liver
    0.38
     Hilton
    0.38
    POSITIVE LOGITS
    boru
    0.44
    ABL
    0.41
    pr
    0.39
    ég
    0.38
    莪
    0.38
    urar
    0.37
    rising
    0.37
    steering
    0.37
    abl
    0.36
     gris
    0.36
    Activations Density 0.000%

    No Known Activations