© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44749
    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_22_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
     Tiere
    0.44
    ាយ
    0.42
    䏹
    0.42
    閲
    0.41
     Música
    0.40
    ُول
    0.40
     éd
    0.39
     Eindruck
    0.39
     تقل
    0.39
     числі
    0.39
    POSITIVE LOGITS
    achts
    0.47
    jeta
    0.46
    oxic
    0.45
    ate
    0.44
     butchers
    0.44
    cuna
    0.44
    ]="
    0.43
    jeff
    0.43
    celand
    0.43
    anging
    0.43
    Activations Density 0.000%

    No Known Activations