© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125936
    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_37_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
    meet
    0.40
     社会
    0.39
     المع
    0.38
     meet
    0.38
    莞
    0.36
    Meet
    0.36
    Johnson
    0.36
     residing
    0.36
    生
    0.36
     මා
    0.36
    POSITIVE LOGITS
     filtration
    0.44
     filtr
    0.43
     filtered
    0.41
     fandom
    0.41
     purification
    0.41
     magnification
    0.41
     superfamily
    0.41
     Family
    0.40
     magnified
    0.40
     Famil
    0.40
    Activations Density 0.000%

    No Known Activations