© 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. 211064
    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
     strains
    0.46
     linked
    0.43
     crosses
    0.43
     لس
    0.43
     provas
    0.42
    تي
    0.42
    들
    0.42
     rech
    0.41
     operativa
    0.41
    桿
    0.41
    POSITIVE LOGITS
    atsby
    0.48
    ame
    0.48
    aéroport
    0.46
     बिंदुओं
    0.45
    pecting
    0.44
    ኝነት
    0.43
    లేని
    0.43
    ఎల్
    0.42
    ⌋
    0.42
    jež
    0.42
    Activations Density 0.000%

    No Known Activations