© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34099
    Prev
    Next
    INDEX
    Explanations

    absolute value

    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_3_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
    .
    0.82
    (
    0.77
    u
    0.71
    ("
    0.71
    *
    0.70
    ;
    0.68
    기
    0.68
     isomerization
    0.64
    er
    0.62
    >
    0.62
    POSITIVE LOGITS
     absolue
    0.80
    absolute
    0.80
    י
    0.79
     Absolute
    0.75
    absol
    0.74
     absolute
    0.71
     Abs
    0.71
     абсолю
    0.70
     مطلق
    0.69
    ם
    0.69
    Activations Density 0.040%

    No Known Activations