© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43401
    Prev
    Next
    INDEX
    Explanations

    work schedule

    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_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
    Idle
    0.27
    Os
    0.24
    DOE
    0.23
    Cost
    0.23
    opengl
    0.23
    이
    0.23
    owe
    0.23
     os
    0.23
    eday
    0.23
    idle
    0.23
    POSITIVE LOGITS
     расс
    0.26
     কম
    0.25
    磺
    0.24
     कमी
    0.23
    മാണ്
    0.23
     послу
    0.23
    nection
    0.23
     ખૂબ
    0.23
     ਵੱ
    0.23
     પોલીસ
    0.23
    Activations Density 0.007%

    No Known Activations