© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    far-right neo-nazi ideologies

    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_15_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
     του
    0.53
     رہ
    0.53
     CO
    0.52
    આ
    0.52
    يط
    0.50
    Sunday
    0.50
    צה
    0.50
    ل
    0.50
     Ins
    0.49
     Fier
    0.49
    POSITIVE LOGITS
    '
    0.52
    illian
    0.52
    ются
    0.51
     religiosas
    0.50
    ained
    0.49
    ovány
    0.49
    ulen
    0.48
     करेंगी
    0.48
    ='/'
    0.48
    uminum
    0.48
    Activations Density 0.006%

    No Known Activations