© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216696
    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_31_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
     imprinted
    0.38
     motorbike
    0.38
    不用
    0.37
     hug
    0.37
     年
    0.36
     गर्म
    0.36
     calibrate
    0.36
     নিউ
    0.36
    =+
    0.35
     stay
    0.35
    POSITIVE LOGITS
     disparition
    0.41
    numerical
    0.40
    Numeric
    0.39
    quota
    0.38
    unc
    0.38
    bloc
    0.36
     Protected
    0.36
    ուն
    0.36
    localized
    0.36
    Numerical
    0.36
    Activations Density 0.000%

    No Known Activations