© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23768
    Prev
    Next
    INDEX
    Explanations

    doujin

    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_56_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
     世
    0.43
     zwró
    0.39
    世
    0.39
     أكثر
    0.38
     여
    0.38
     established
    0.37
     operation
    0.36
     оче
    0.35
     Outer
    0.35
     conveniente
    0.35
    POSITIVE LOGITS
    通
    1.13
     통
    0.91
    に通
    0.81
    통
    0.78
     tong
    0.75
     通
    0.73
    Tong
    0.61
     thông
    0.59
     Tong
    0.57
    tong
    0.56
    Activations Density 0.001%

    No Known Activations