© 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. 39518
    Prev
    Next
    INDEX
    Explanations

    colonialism

    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
    t
    0.88
    -
    0.82
    er
    0.77
    ت
    0.74
    ed
    0.73
    ι
    0.71
    .
    0.70
    AI
    0.68
    to
    0.68
    ling
    0.67
    POSITIVE LOGITS
    கிறது
    0.82
     affirme
    0.71
     Ángeles
    0.71
     arrive
    0.70
    شہ
    0.69
    ন
    0.68
     attaque
    0.68
     Ekim
    0.66
     etre
    0.66
    fireplace
    0.65
    Activations Density 0.006%

    No Known Activations