© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113542
    Prev
    Next
    INDEX
    Explanations

    synesthesia

    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
    Negative Logits
     in
    1.16
    ene
    1.15
    dale
    0.99
        
    0.96
    ells
    0.95
    <0xBE>
    0.87
    iving
    0.86
    elijk
    0.85
    nite
    0.85
    opausal
    0.84
    POSITIVE LOGITS
    ০
    1.55
    ك
    1.48
    ли
    1.39
    p
    1.38
    𝟬
    1.38
    هم
    1.34
    你
    1.33
    0
    1.32
    ０
    1.30
    то
    1.26
    Activations Density 0.000%

    No Known Activations