© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142573
    Prev
    Next
    INDEX
    Explanations

    car colors and finishes

    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_12_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
    高志森
    0.46
     lockout
    0.45
     प्रथा
    0.45
    தைய
    0.45
    PCR
    0.43
     prosecute
    0.42
    殖
    0.42
    слови
    0.42
    ၞ
    0.42
    قوم
    0.41
    POSITIVE LOGITS
    āja
    0.47
    ренный
    0.46
    em
    0.45
    unjukkan
    0.44
     joyful
    0.43
     turquoise
    0.43
     Trebuie
    0.43
     brillante
    0.42
     charisma
    0.42
     bayan
    0.41
    Activations Density 0.002%

    No Known Activations