© 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. 85175
    Prev
    Next
    INDEX
    Explanations

    United States or names

    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
    ق
    0.67
    ص
    0.66
    碜
    0.60
    お客様
    0.60
    cısı
    0.59
    }];
    0.59
    ه
    0.59
    ئي
    0.58
    urra
    0.58
    }]},
    0.57
    POSITIVE LOGITS
    frac
    0.54
    ลก
    0.53
     і
    0.52
    .')
    0.52
     गुजर
    0.51
    с
    0.51
     }
    0.50
    >';
    0.50
    면
    0.50
    闻
    0.50
    Activations Density 0.000%

    No Known Activations