© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66410
    Prev
    Next
    INDEX
    Explanations

    out of

    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_41_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
     सीएस
    0.43
     Cs
    0.41
     cs
    0.41
     CS
    0.41
    CS
    0.38
    ीडी
    0.37
     погре
    0.37
    ))}{
    0.37
    Cs
    0.36
     MOD
    0.36
    POSITIVE LOGITS
     out
    1.38
     outta
    1.20
    outof
    1.04
    OutOf
    0.94
     Out
    0.89
     из
    0.88
    Out
    0.86
    out
    0.77
     आउट
    0.74
     OUT
    0.70
    Activations Density 0.075%

    No Known Activations