© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 529
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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_44_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
    StarCore
    0.55
     dvara
    0.54
     coval
    0.49
    लिट
    0.49
     guitarra
    0.48
    ㄼ
    0.48
     força
    0.47
     Hfn
    0.47
    🙎
    0.47
    tFileInputExcel
    0.47
    POSITIVE LOGITS
     k
    0.54
     m
    0.45
     h
    0.44
     hang
    0.43
     D
    0.42
     K
    0.42
     t
    0.42
     w
    0.41
     tak
    0.41
    p
    0.40
    Activations Density 0.006%

    No Known Activations