© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11952
    Prev
    Next
    INDEX
    Explanations

    represented by its legal representative

    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_40_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
     alltid
    0.40
    itures
    0.39
    icoter
    0.38
     raken
    0.38
    暑
    0.37
    othing
    0.36
     चंद्रमा
    0.36
    വാസ
    0.36
     ℝ
    0.36
    ალური
    0.35
    POSITIVE LOGITS
     citizen
    0.48
     Citizen
    0.43
    citizen
    0.41
     mosaic
    0.38
     worker
    0.37
     Worker
    0.37
     Balance
    0.37
    fork
    0.37
    ipan
    0.37
     cold
    0.37
    Activations Density 0.017%

    No Known Activations