© 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. 175284
    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_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
     lymphatic
    0.50
     disturbed
    0.47
     projective
    0.46
     affliction
    0.46
    𒊒
    0.45
     Sime
    0.45
     मम
    0.45
    淦
    0.44
     varsity
    0.44
     reckoned
    0.44
    POSITIVE LOGITS
    ott
    0.54
     Thế
    0.43
    å
    0.43
     Pret
    0.42
     GUIDE
    0.41
    Ciudad
    0.41
    ाल
    0.40
    \%,
    0.40
    coaster
    0.40
    xlsx
    0.39
    Activations Density 0.000%

    No Known Activations