© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51733
    Prev
    Next
    INDEX
    Explanations

    final or const followed by type

    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_10_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
    ल
    0.71
    استشهاد
    0.67
    Ặ
    0.67
    лью
    0.66
    ল
    0.63
    एगा
    0.63
    лай
    0.62
    hasClass
    0.62
    महल
    0.62
    లుగా
    0.61
    POSITIVE LOGITS
    ed
    0.89
    a
    0.87
    r
    0.87
    :
    0.73
    0.72
    )
    0.71
    ue
    0.70
    }
    0.68
    at
    0.67
    ]
    0.64
    Activations Density 0.001%

    No Known Activations