© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78397
    Prev
    Next
    INDEX
    Explanations

    embark or IDC

    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_0_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
    AN
    1.38
    :
    1.27
    "
    1.17
     clashes
    1.16
     stains
    1.13
    in
    1.11
     trusts
    1.05
     sweats
    1.04
    在
    1.04
    un
    1.03
    POSITIVE LOGITS
    ী
    1.69
     that
    1.50
    い
    1.49
    have
    1.45
    that
    1.43
    ното
    1.42
    ת
    1.41
     with
    1.35
    ні
    1.35
    ä
    1.33
    Activations Density 0.000%

    No Known Activations