© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11235
    Prev
    Next
    INDEX
    Explanations

    glasses

    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_13_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
    啤
    0.51
     printed
    0.50
    d
    0.50
     flipped
    0.48
     printer
    0.48
     volum
    0.47
    0.47
     boat
    0.46
     printing
    0.46
     leaked
    0.46
    POSITIVE LOGITS
    𒍑
    0.58
    ysz
    0.56
     droit
    0.55
     ይች
    0.54
    ორი
    0.53
     rédaction
    0.50
     время
    0.50
    сток
    0.50
    侸
    0.50
    ustus
    0.49
    Activations Density 0.000%

    No Known Activations