© 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. 113315
    Prev
    Next
    INDEX
    Explanations

    tax cuts

    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_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
    ),
    1.34
    ).
    0.93
    );
    0.90
    ],
    0.88
    ó
    0.87
    K
    0.86
    );}
    0.84
    0.82
    },
    0.79
    )">
    0.78
    POSITIVE LOGITS
    in
    1.00
    s
    0.99
    ون
    0.89
    ی
    0.86
    ۲
    0.85
    이면
    0.85
    kowe
    0.84
    a
    0.84
    ne
    0.83
    ের
    0.83
    Activations Density 0.000%

    No Known Activations