© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54070
    Prev
    Next
    INDEX
    Explanations

    they defeated

    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_31_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
    ပို
    0.37
    組
    0.33
    团队
    0.33
     команд
    0.32
    衍
    0.32
     Commandant
    0.32
     واپ
    0.32
    anship
    0.31
    imt
    0.31
     commandant
    0.31
    POSITIVE LOGITS
     ध्यान
    0.36
    ◾
    0.36
    Respect
    0.36
     duplicates
    0.35
    Sarah
    0.35
     অনুরোধ
    0.34
    .$
    0.33
     duplicate
    0.33
     Duplicate
    0.33
    Reach
    0.33
    Activations Density 0.002%

    No Known Activations