© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46725
    Prev
    Next
    INDEX
    Explanations

    bullying and mean behavior

    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_13_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
    jaa
    0.51
    ra
    0.50
    kość
    0.49
     otp
    0.48
    d
    0.48
    svp
    0.48
    subtree
    0.48
    ěk
    0.47
     சிவா
    0.47
    Luca
    0.47
    POSITIVE LOGITS
     bullying
    0.79
     corrosive
    0.62
    '
    0.61
     harassment
    0.59
     intravascular
    0.59
     dehumid
    0.57
     bully
    0.56
     sepsis
    0.55
     intimidation
    0.55
     interpersonal
    0.54
    Activations Density 0.056%

    No Known Activations