© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178996
    Prev
    Next
    INDEX
    Explanations

    B/P abbreviations

    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_50_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
     op
    0.48
    P
    0.45
     Shapiro
    0.43
    瘋
    0.39
    op
    0.39
    apiro
    0.38
     indefin
    0.38
    Madison
    0.38
    incarn
    0.37
    PAP
    0.37
    POSITIVE LOGITS
     B
    0.49
    ced
    0.42
    CASCADE
    0.42
    xB
    0.40
     Maxime
    0.40
     CSC
    0.40
    CS
    0.39
    ca
    0.39
    КС
    0.38
    𒀝
    0.38
    Activations Density 0.001%

    No Known Activations