© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211780
    Prev
    Next
    INDEX
    Explanations

    ping command

    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_20_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
    adaptive
    0.38
    ax
    0.36
    बिया
    0.36
    <0xC2>
    0.35
    ایر
    0.35
    忻
    0.35
    iential
    0.35
    linearity
    0.35
    운동
    0.35
    ='
    0.34
    POSITIVE LOGITS
     פון
    0.45
    rž
    0.44
     Geburtstag
    0.43
     entfer
    0.43
     vết
    0.42
    ęk
    0.41
     controversy
    0.41
    Lanc
    0.40
     amelyek
    0.40
     ৪৮
    0.40
    Activations Density 0.003%

    No Known Activations