© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141321
    Prev
    Next
    INDEX
    Explanations

    perpetuates, stereotypes, positioning, restrictions

    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_12_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
    ಮ
    0.50
    هِ
    0.49
     makes
    0.48
    ucks
    0.48
    ierta
    0.48
    ownt
    0.47
    ương
    0.47
    akang
    0.47
    we
    0.46
     Bang
    0.46
    POSITIVE LOGITS
    秝
    0.63
     Porém
    0.56
     તેમની
    0.56
     với
    0.53
     ți
    0.52
    勃
    0.52
     livre
    0.51
     स्थाई
    0.51
     دیتے
    0.50
     pcMove
    0.49
    Activations Density 0.012%

    No Known Activations