© 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. 199094
    Prev
    Next
    INDEX
    Explanations

    combating hate speech

    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
     gnome
    0.59
    yses
    0.57
     amu
    0.57
     ފ
    0.56
     Smo
    0.56
     기
    0.56
     cord
    0.55
     Cord
    0.55
     moons
    0.55
     aliv
    0.55
    POSITIVE LOGITS
    7
    0.57
    the
    0.50
    t
    0.50
    <0x0D>
    0.49
    ت
    0.49
    ப
    0.48
     हमले
    0.48
    atly
    0.47
    4
    0.47
    ओं
    0.47
    Activations Density 0.012%

    No Known Activations