© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211113
    Prev
    Next
    INDEX
    Explanations

    berries

    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_20_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
     resistenza
    0.41
     всіх
    0.41
     benutzt
    0.40
     план
    0.39
    控
    0.39
    рактеристики
    0.39
     ഇത്
    0.39
     firewood
    0.39
     discouraging
    0.39
    ControlButton
    0.38
    POSITIVE LOGITS
    factors
    0.41
    Ric
    0.41
    bis
    0.40
    asic
    0.40
    Indigenous
    0.40
    travel
    0.39
     masterpiece
    0.39
    ***
    0.39
    каче
    0.39
    singer
    0.39
    Activations Density 0.001%

    No Known Activations