© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41499
    Prev
    Next
    INDEX
    Explanations

    Kahului Airport

    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_3_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
    י
    0.71
    不過
    0.61
    ANCE
    0.60
    ന്ഥ
    0.60
     lard
    0.59
    W
    0.59
    来
    0.59
     raf
    0.59
    ין
    0.58
    يف
    0.58
    POSITIVE LOGITS
     Anschluss
    0.55
     Stiffness
    0.55
    textt
    0.54
     Chinn
    0.54
    ymmetry
    0.54
    gling
    0.54
     Analyzing
    0.53
     neoplasms
    0.52
    творення
    0.52
    摖
    0.52
    Activations Density 0.000%

    No Known Activations