© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91306
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     u
    0.43
     х
    0.42
     x
    0.40
     ма
    0.40
     t
    0.40
     Ma
    0.40
     o
    0.38
     a
    0.37
     type
    0.37
     s
    0.36
    POSITIVE LOGITS
    '
    0.50
    wick
    0.50
    ska
    0.49
    kimi
    0.47
    (
    0.45
    sene
    0.44
    Ễ
    0.43
    nali
    0.42
    kira
    0.42
    kte
    0.42
    Activations Density 0.001%

    No Known Activations