© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250322
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     shift
    0.47
    shift
    0.43
    SignedIn
    0.42
    Shift
    0.41
    품
    0.41
    ряду
    0.40
     Depends
    0.40
     depends
    0.38
     Shift
    0.38
     build
    0.38
    POSITIVE LOGITS
     точно
    0.39
    上来
    0.37
    average
    0.37
    properties
    0.36
    Average
    0.35
     गर्व
    0.35
    ensington
    0.35
     PROPERTIES
    0.34
    يرا
    0.34
     و
    0.34
    Activations Density 0.000%

    No Known Activations