© 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. 17587
    Prev
    Next
    INDEX
    Explanations

    Bund, Bundestag, Bottlebrush, Bottlenose

    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
    ඟ
    0.48
    Comp
    0.44
    pegno
    0.39
     Advancement
    0.38
    ahertz
    0.37
    Deletion
    0.37
    GetComponent
    0.37
    Th
    0.36
    ंता
    0.36
    ニ
    0.36
    POSITIVE LOGITS
     bund
    0.39
     forage
    0.38
     foraging
    0.38
     Bund
    0.37
     LOAD
    0.37
    േ
    0.37
    紧
    0.37
     practicality
    0.37
     variational
    0.36
     trustworthiness
    0.36
    Activations Density 0.008%

    No Known Activations