© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40648
    Prev
    Next
    INDEX
    Explanations

    Lagavulin or Margarita

    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_3_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
     كرد
    0.79
    لي
    0.76
     كان
    0.75
    ен
    0.75
    ين
    0.73
    от
    0.70
     Jess
    0.64
    স
    0.64
    об
    0.63
    ير
    0.63
    POSITIVE LOGITS
    ;
    0.85
    (
    0.84
    "
    0.79
    2
    0.73
    ۔
    0.71
    )
    0.69
    ]
    0.64
     of
    0.59
    beat
    0.59
    forum
    0.58
    Activations Density 0.000%

    No Known Activations