© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225857
    Prev
    Next
    INDEX
    Explanations

    ENTIRE SECTION

    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_10_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
    는
    1.10
    是
    1.05
    은
    0.93
    は
    0.86
    }=\
    0.83
    h
    0.80
    ۔
    0.79
    }-\
    0.78
    }+\
    0.76
    ৬
    0.75
    POSITIVE LOGITS
    at
    1.09
    f
    0.87
    ang
    0.82
     o
    0.78
    LE
    0.76
     ICU
    0.75
    ure
    0.74
     LE
    0.73
    who
    0.72
    hearted
    0.72
    Activations Density 0.000%

    No Known Activations