© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1167
    Prev
    Next
    INDEX
    Explanations

    ip addr, ip link, Fedora, RH

    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_39_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
    пар
    0.41
    caling
    0.40
    利
    0.38
    isdir
    0.37
     बीसीजी
    0.37
     borders
    0.37
     расши
    0.36
     pancreas
    0.36
     dược
    0.36
    ረስ
    0.36
    POSITIVE LOGITS
     upstream
    0.41
     Bugs
    0.40
     Bug
    0.39
     SSH
    0.38
    SSH
    0.38
     downstream
    0.38
     bugs
    0.38
    瓮
    0.38
     bug
    0.37
    RH
    0.37
    Activations Density 0.191%

    No Known Activations