© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15210
    Prev
    Next
    INDEX
    Explanations

    separators

    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
    Negative Logits
    מ
    0.41
    ي
    0.41
     augmenter
    0.38
     avoir
    0.37
     mantenere
    0.37
     WOULD
    0.36
    ﻣ
    0.36
     rebounds
    0.36
    y
    0.36
    <unused2141>
    0.35
    POSITIVE LOGITS
    ስቃ
    0.35
    ̣
    0.33
    लेषण
    0.32
    owana
    0.32
    प्लो
    0.32
    forma
    0.32
    project
    0.31
    icken
    0.31
    nienia
    0.31
    romagn
    0.31
    Activations Density 0.072%

    No Known Activations