© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136184
    Prev
    Next
    INDEX
    Explanations

    computational linguistics and methods

    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
    Negative Logits
    綻
    0.56
    תן
    0.54
     "-"]
    0.49
    カナ
    0.49
     citrate
    0.48
     filings
    0.46
     nutric
    0.46
    菠
    0.46
     proline
    0.46
    탑
    0.46
    POSITIVE LOGITS
    um
    0.66
    al
    0.61
    am
    0.60
    em
    0.57
    zné
    0.56
    ae
    0.55
    /
    0.54
    ænd
    0.54
    microsoft
    0.54
    ://
    0.53
    Activations Density 0.001%

    No Known Activations