© 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. 108155
    Prev
    Next
    INDEX
    Explanations

    CAD/CAM software

    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
    ra
    1.34
    '
    1.21
    मा
    1.20
    ور
    1.10
    ad
    1.05
    ul
    1.05
    se
    1.03
    v
    1.00
    ry
    0.98
    ni
    0.96
    POSITIVE LOGITS
    ه
    1.29
    0
    1.24
     lanz
    1.22
    ()=>{
    1.20
    很
    1.09
    ۰۰
    1.08
     designado
    1.03
     contrat
    1.02
     mezcl
    1.00
    ０
    0.99
    Activations Density 0.000%

    No Known Activations