© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237126
    Prev
    Next
    INDEX
    Explanations

    numbers in context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     MOL
    0.61
     Mol
    0.58
     MR
    0.57
     M
    0.54
     П
    0.51
    Ｍ
    0.51
     P
    0.50
    MR
    0.50
    Mol
    0.50
    M
    0.49
    POSITIVE LOGITS
    ishu
    0.40
    ranu
    0.37
     سرخ
    0.36
    lone
    0.36
    Deck
    0.36
     ઉજ
    0.36
    rij
    0.35
    ฟา
    0.35
     aja
    0.35
    newMark
    0.35
    Activations Density 0.016%

    No Known Activations