© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132804
    Prev
    Next
    INDEX
    Explanations

    Gloomhaven

    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_1_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
    る
    1.68
    고
    1.34
    dır
    1.30
    d
    1.25
     банки
    1.16
    ль
    1.15
     गाने
    1.13
     bruises
    1.13
     SLAs
    1.13
     malicious
    1.11
    POSITIVE LOGITS
    am
    1.50
    for
    1.46
    ى
    1.32
    0
    1.27
    ang
    1.23
    RE
    1.20
    an
    1.20
    if
    1.13
    RA
    1.05
    ab
    1.05
    Activations Density 0.001%

    No Known Activations