© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40273
    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_57_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
    埴
    0.40
    噔
    0.40
    禣
    0.40
    protection
    0.39
    ɧ
    0.39
    htub
    0.39
     җиңү
    0.39
    आरपी
    0.39
     пришлось
    0.38
    쉴
    0.38
    POSITIVE LOGITS
     Serv
    0.76
     Servo
    0.71
    Serv
    0.70
     Ser
    0.64
     serv
    0.63
     Servers
    0.61
     servers
    0.61
    serv
    0.59
     Server
    0.59
     server
    0.57
    Activations Density 0.000%

    No Known Activations