© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    radiology reports or medical scans

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दिवा
    0.36
    गानिस्तान
    0.35
    径
    0.35
     Multivariate
    0.34
    炷
    0.34
    Ᏻ
    0.34
    segment
    0.34
     tenetur
    0.34
    ᅧ
    0.34
    ☦
    0.33
    POSITIVE LOGITS
     novel
    0.50
     Novel
    0.49
     Complexes
    0.46
     COMPLEXES
    0.44
    Novel
    0.43
     complexes
    0.42
     Compounds
    0.41
     NOS
    0.41
    Compounds
    0.41
     COMPOUNDS
    0.41
    Activations Density 0.073%

    No Known Activations