© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89199
    Prev
    Next
    INDEX
    Explanations

    True

    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_60_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
    хе
    0.38
     *,
    0.37
    ,\
    0.37
    ,\,\
    0.37
    ıl
    0.36
     ,\
    0.36
     *\
    0.36
    یس
    0.36
    انس
    0.35
    ूले
    0.35
    POSITIVE LOGITS
     ou
    0.83
     Ou
    0.75
     OU
    0.74
     eller
    0.66
    Ou
    0.65
     edo
    0.63
    fake
    0.62
     або
    0.61
    false
    0.59
     Eller
    0.59
    Activations Density 0.001%

    No Known Activations