© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2877
    Prev
    Next
    INDEX
    Explanations

    Controller, Repository, Mappings

    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_39_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
     losses
    0.44
    losses
    0.44
     trest
    0.39
     MAIN
    0.38
     loses
    0.38
     telescope
    0.38
     chefs
    0.38
    損
    0.38
    Improvements
    0.37
     sums
    0.37
    POSITIVE LOGITS
     Tags
    0.44
    POSITORY
    0.40
    pom
    0.38
    洹
    0.38
    Repository
    0.37
    անի
    0.37
     不要
    0.37
    BrNO
    0.37
     internal
    0.36
     рези
    0.36
    Activations Density 0.001%

    No Known Activations