© 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. 121403
    Prev
    Next
    INDEX
    Explanations

    Archduke Franz Ferdinand Bulldog

    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
    ။
    0.68
    ك
    0.66
    。
    0.65
    }
    0.61
    ről
    0.60
     jedes
    0.60
    }],
    0.58
    ]
    0.58
     be
    0.57
    os
    0.57
    POSITIVE LOGITS
    ing
    0.71
    <0x0D>
    0.66
    ะ
    0.58
    ни
    0.58
    is
    0.57
     রশিদ
    0.57
    рия
    0.57
     Russie
    0.56
    u
    0.56
    ath
    0.56
    Activations Density 0.001%

    No Known Activations