© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231789
    Prev
    Next
    INDEX
    Explanations

    longevidad, envejecimiento

    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
    ۔
    1.46
    ።
    1.30
    は
    1.29
    는
    1.27
    。
    1.20
    ના
    1.14
     It
    1.07
    ی
    1.00
    是
    1.00
    க்கு
    0.88
    POSITIVE LOGITS
    ;
    2.14
    <0x80>
    1.39
    o
    1.28
    지
    1.23
    та
    1.20
    ,
    1.18
    ки
    1.12
    y
    1.09
    z
    1.09
    า
    1.08
    Activations Density 0.000%

    No Known Activations