© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 213836
    Prev
    Next
    INDEX
    Explanations

    0

    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_47_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
    :///
    0.38
    Concrete
    0.36
    遛
    0.36
    Lead
    0.35
    Lett
    0.35
    XY
    0.34
     discrete
    0.34
    newPage
    0.34
    ABB
    0.34
    insulated
    0.34
    POSITIVE LOGITS
     Nine
    0.50
     ۹
    0.49
    九
    0.49
     ९
    0.46
     Ninety
    0.45
     Sloane
    0.45
     nine
    0.45
     labours
    0.44
     九
    0.43
     नाइन
    0.43
    Activations Density 0.000%

    No Known Activations