© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204426
    Prev
    Next
    INDEX
    Explanations

    SLE and sleep, often in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     乀
    1.02
    ят
    0.92
    motionProxy
    0.91
    يند
    0.91
    timevals
    0.89
     будь
    0.85
    kaan
    0.84
     APIDC
    0.82
     descrito
    0.82
    дился
    0.82
    POSITIVE LOGITS
     It
    1.30
     The
    1.25
    0
    1.22
     There
    1.09
    It
    1.07
     That
    1.05
     In
    1.04
     If
    1.04
    What
    1.02
    If
    1.01
    Activations Density 0.000%

    No Known Activations