© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193608
    Prev
    Next
    INDEX
    Explanations

    daughter or mom

    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_4_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
    .
    1.13
    the
    1.05
    л
    1.02
    ม
    0.96
    ت
    0.95
    ↵
    0.88
    nya
    0.88
    ุ
    0.87
    ต์
    0.84
    יי
    0.81
    POSITIVE LOGITS
    ﻜ
    0.74
    ruption
    0.71
     ГӀ
    0.71
     Κο
    0.70
    ponding
    0.68
    rierung
    0.66
    rières
    0.66
    iiv
    0.66
    p
    0.65
    olées
    0.64
    Activations Density 0.021%

    No Known Activations