© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102604
    Prev
    Next
    INDEX
    Explanations

    lists with asterisk formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_14_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
     прошло
    0.61
     imprese
    0.55
     incumpl
    0.53
     &=&
    0.53
     printemps
    0.52
    _-
    0.50
    ница
    0.50
    ács
    0.50
     invierno
    0.49
     verge
    0.49
    POSITIVE LOGITS
     Device
    0.48
     मधुमेह
    0.45
    Server
    0.45
     biomarker
    0.43
    Sexo
    0.43
    鐏
    0.43
    糖尿病
    0.42
    荷重
    0.42
     bondage
    0.42
    źdz
    0.41
    Activations Density 0.000%

    No Known Activations