© 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. 62884
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ]
    1.20
     in
    1.16
    }
    1.13
    ود
    0.99
    "
    0.91
    ధ
    0.88
     Agreements
    0.87
    د
    0.86
     Textile
    0.85
    "}
    0.85
    POSITIVE LOGITS
    ка
    1.43
    uje
    1.27
    க்கு
    1.26
    ん
    1.16
    j
    1.16
    くない
    1.13
    ра
    1.11
    arı
    1.10
    রকম
    1.10
    мимо
    1.09
    Activations Density 0.000%

    No Known Activations