© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41121
    Prev
    Next
    INDEX
    Explanations

    specifies the

    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_11_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
    }"]
    0.48
    ৯
    0.46
     Inner
    0.45
    }]$,
    0.45
    ﹊
    0.45
    })\
    0.45
     embroidered
    0.45
     கூட்டணி
    0.45
     وصلنا
    0.45
    INNER
    0.45
    POSITIVE LOGITS
    in
    0.54
    る
    0.54
    то
    0.53
    P
    0.52
    as
    0.51
    There
    0.51
    even
    0.49
    ů
    0.48
    2
    0.48
    </blockquote>
    0.48
    Activations Density 0.008%

    No Known Activations