© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157388
    Prev
    Next
    INDEX
    Explanations

    lounge zone

    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_2_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
    지
    1.51
     on
    1.34
    ال
    1.28
    r
    1.25
     is
    1.22
    大
    1.16
    ون
    1.16
    top
    1.09
    ים
    1.09
    ють
    1.06
    POSITIVE LOGITS
    </b>
    0.96
     reconoc
    0.94
    ,}
    0.92
     a
    0.92
     médicos
    0.91
     но
    0.91
     ದ
    0.90
     atteint
    0.89
     sofern
    0.89
     вами
    0.89
    Activations Density 0.000%

    No Known Activations