© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62492
    Prev
    Next
    INDEX
    Explanations

    real

    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_59_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
     real
    4.06
     реа
    3.59
    real
    3.22
     रियल
    2.81
    实
    2.81
    Real
    2.75
    実
    2.66
     실
    2.56
     REAL
    2.55
    REAL
    2.53
    POSITIVE LOGITS
     Rä
    0.37
    ebug
    0.36
    стами
    0.35
    EEP
    0.34
     რ
    0.33
     রেজা
    0.33
    ృష్ణ
    0.32
    ೆಗೆ
    0.31
    ležit
    0.31
    ടതി
    0.31
    Activations Density 0.107%

    No Known Activations