© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87143
    Prev
    Next
    INDEX
    Explanations

    Racial justice

    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_3_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
    కు
    0.69
    ุ
    0.69
    ных
    0.65
    が多く
    0.63
    ات
    0.63
    ного
    0.63
    ری
    0.63
     pergunta
    0.59
    og
    0.59
     branca
    0.59
    POSITIVE LOGITS
    N
    0.64
    MIS
    0.62
    お
    0.62
    MT
    0.61
    MED
    0.61
    incón
    0.59
    𝙈
    0.59
    もら
    0.58
     учё
    0.58
    U
    0.57
    Activations Density 0.002%

    No Known Activations