© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241557
    Prev
    Next
    INDEX
    Explanations

    nbcnews.com links, names, organizations

    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_40_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
    odimensional
    0.43
     kredit
    0.41
    redients
    0.41
     Tod
    0.40
     currentRow
    0.40
     რამდენ
    0.39
     LOGIN
    0.39
    渠
    0.39
     kredi
    0.38
     ferro
    0.38
    POSITIVE LOGITS
    integrated
    0.39
     एना
    0.38
    Gib
    0.38
     කෙ
    0.37
    收获
    0.37
    ёр
    0.36
    coordinated
    0.36
    throws
    0.35
    yield
    0.35
    harvest
    0.35
    Activations Density 0.013%

    No Known Activations