© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222081
    Prev
    Next
    INDEX
    Explanations

    URLs for government (.gov, .nhs.uk, .who.int) and official sites

    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_10_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
    掑
    0.28
     Supper
    0.27
     Analytics
    0.26
     Office
    0.26
     Paper
    0.26
    O
    0.26
    K
    0.25
    ’
    0.25
    Q
    0.25
     Things
    0.25
    POSITIVE LOGITS
    v
    0.46
    h
    0.38
    3
    0.36
    ado
    0.35
    hla
    0.34
    t
    0.34
     that
    0.32
    yı
    0.31
    は
    0.31
    1
    0.31
    Activations Density 0.009%

    No Known Activations