© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13623
    Prev
    Next
    INDEX
    Explanations

    "you know" and "oh"

    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_13_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
    ي
    0.57
    i
    0.56
     reimbursed
    0.45
    वंत
    0.45
    iere
    0.43
    י
    0.43
     reimbursement
    0.42
     mito
    0.41
     cometido
    0.41
    িলারা
    0.41
    POSITIVE LOGITS
    る
    0.53
    Р
    0.51
    ة
    0.48
    ين
    0.48
    ات
    0.47
    ında
    0.47
    x
    0.47
    p
    0.45
    장
    0.45
    ad
    0.45
    Activations Density 0.018%

    No Known Activations