© 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. 207509
    Prev
    Next
    INDEX
    Explanations

    working conditions

    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
     безопас
    0.42
    charset
    0.42
    휘
    0.41
     vm
    0.40
     newsp
    0.40
     bezpie
    0.39
    isham
    0.38
    Myst
    0.38
    Rate
    0.38
     خودرو
    0.37
    POSITIVE LOGITS
    ტიკ
    0.38
     Canyon
    0.38
    TED
    0.36
    לך
    0.36
    羡
    0.35
    yel
    0.35
     TED
    0.35
    TAL
    0.35
     tackles
    0.34
     재생
    0.34
    Activations Density 0.001%

    No Known Activations