© 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. 195297
    Prev
    Next
    INDEX
    Explanations

    Eichmann, Nazis, Holocaust

    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
    bi
    0.56
     Here
    0.55
    ání
    0.52
     Playoffs
    0.52
     ஃ
    0.52
     if
    0.51
    𒅗
    0.50
    кт
    0.49
    Cliff
    0.47
     jitter
    0.46
    POSITIVE LOGITS
    или
    0.57
    들에게
    0.57
    ()],
    0.54
    のための
    0.53
    ంథ
    0.52
    Зна
    0.52
    下面的
    0.51
    Л
    0.51
    下の
    0.50
     혹은
    0.50
    Activations Density 0.002%

    No Known Activations