© 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. 258330
    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
    S
    0.45
    3
    0.44
     кирпи
    0.43
     строительства
    0.42
     recollections
    0.42
     numeric
    0.42
     calibrations
    0.40
     bolder
    0.39
    뻘
    0.38
    4
    0.38
    POSITIVE LOGITS
     Turnier
    0.44
     Luch
    0.43
    弈
    0.43
     rea
    0.40
     梅
    0.40
    ilig
    0.40
    ಕ್ಕಾಗಿ
    0.40
    मो
    0.40
     Medien
    0.39
    ạo
    0.39
    Activations Density 0.000%

    No Known Activations