© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40432
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_57_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
    ulación
    0.40
    ítmény
    0.36
     जातीय
    0.35
    军
    0.34
    antiation
    0.34
    clamation
    0.33
    度の
    0.33
    ='"
    0.33
     Apol
    0.33
     휘
    0.32
    POSITIVE LOGITS
    textrm
    0.37
     сопровожда
    0.34
    gged
    0.33
    blogspot
    0.33
    rimi
    0.33
    unknown
    0.32
     देकर
    0.32
     Paste
    0.32
    ebu
    0.32
     אותו
    0.32
    Activations Density 0.032%

    No Known Activations