© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136573
    Prev
    Next
    INDEX
    Explanations

    yes or no classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    ﻔ
    0.80
     홍
    0.60
    TION
    0.58
     Dyed
    0.57
    CRO
    0.57
     söyled
    0.56
    LAGAB
    0.55
    OUGHT
    0.55
    Zm
    0.55
    TNumber
    0.55
    POSITIVE LOGITS
     equations
    0.51
     braces
    0.51
    '
    0.50
     omissions
    0.50
     assignment
    0.50
     over
    0.49
    .”
    0.49
    lement
    0.48
     houses
    0.48
     canvas
    0.48
    Activations Density 0.006%

    No Known Activations