© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61679
    Prev
    Next
    INDEX
    Explanations

    unacceptably sexual or high

    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_11_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
    ण्डा
    0.52
    -
    0.46
     spinner
    0.43
    /
    0.43
     WD
    0.43
    0.41
     guide
    0.41
     Guides
    0.40
    aday
    0.40
     clip
    0.40
    POSITIVE LOGITS
     تأثير
    0.50
    CurrentByte
    0.50
    මන්
    0.49
     Riding
    0.49
     도
    0.49
     пользу
    0.49
     వ్యక్
    0.49
    robespierre
    0.48
    IllegalArgument
    0.48
     কীটপত
    0.48
    Activations Density 0.000%

    No Known Activations