© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171855
    Prev
    Next
    INDEX
    Explanations

    garage, hangar, shed

    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_20_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
    oz
    0.40
     生活
    0.37
     زن
    0.37
    pInBuffer
    0.35
    qz
    0.35
    呮
    0.35
     ミ
    0.34
     اعلی
    0.34
    лами
    0.33
     Parisi
    0.33
    POSITIVE LOGITS
     bangunan
    0.39
     bâtiment
    0.37
     budynku
    0.37
     salvage
    0.37
     FID
    0.37
     assemble
    0.36
     fid
    0.36
    或
    0.36
     onTap
    0.35
     ripet
    0.34
    Activations Density 0.000%

    No Known Activations