© 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. 136278
    Prev
    Next
    INDEX
    Explanations

    East Coast / Hotel / VAT / monkeys / EODC

    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
    ...]
    0.59
    ку
    0.54
    ()].
    0.54
    ادي
    0.53
    উ
    0.53
    ];
    0.52
    Reducer
    0.52
    ]
    0.52
    ｸ
    0.52
    уд
    0.51
    POSITIVE LOGITS
    খাল
    0.52
    🗻
    0.51
     territo
    0.50
    entino
    0.49
     ncols
    0.48
    礦
    0.48
    䉼
    0.48
    zers
    0.48
    䊂
    0.47
    ண்டை
    0.47
    Activations Density 0.001%

    No Known Activations