© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51052
    Prev
    Next
    INDEX
    Explanations

    am

    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_55_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
    бла
    0.43
    eric
    0.38
    Variance
    0.38
    ವೇ
    0.37
    ABET
    0.37
    差
    0.36
    Campus
    0.36
    鐧
    0.36
    اله
    0.36
    ERIC
    0.35
    POSITIVE LOGITS
     drinking
    0.47
     mim
    0.45
     inde
    0.42
     composing
    0.42
     Cucumber
    0.41
     collecting
    0.41
     asking
    0.40
     struggling
    0.40
     cucumber
    0.40
     being
    0.39
    Activations Density 0.002%

    No Known Activations