© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194455
    Prev
    Next
    INDEX
    Explanations

    galactorrhea or galactosidase

    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_4_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
    м
    1.30
    ,
    1.03
    م
    0.96
    ו
    0.90
    ம்
    0.90
    ور
    0.86
    ം
    0.84
    ни
    0.79
    й
    0.77
    (
    0.76
    POSITIVE LOGITS
    s
    0.89
    ed
    0.86
    to
    0.86
    in
    0.82
    een
    0.80
     on
    0.79
    din
    0.79
    𝙩
    0.76
    ting
    0.75
    ds
    0.75
    Activations Density 0.001%

    No Known Activations