© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200476
    Prev
    Next
    INDEX
    Explanations

    radiographs and imaging reports

    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_6_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
    ين
    1.16
    ция
    1.03
    书
    1.02
    ба
    0.97
    са
    0.96
     但是
    0.95
     في
    0.94
    光
    0.93
     entice
    0.92
    會
    0.89
    POSITIVE LOGITS
    im
    1.38
    ]
    1.33
    res
    1.32
    )
    1.32
    I
    1.31
    ok
    1.27
    us
    1.20
    }
    1.20
    é
    1.19
    st
    1.18
    Activations Density 0.000%

    No Known Activations