© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138786
    Prev
    Next
    INDEX
    Explanations

    kidney damage and related conditions

    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_12_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
    နေရာ
    0.51
     Başkan
    0.48
    >')
    0.48
     Dard
    0.46
    ਖ਼
    0.46
     klanten
    0.45
     erfolgen
    0.45
    出来ない
    0.44
     {})
    0.44
    менен
    0.43
    POSITIVE LOGITS
    IS
    0.63
     Га
    0.56
     Му
    0.55
     추
    0.53
     eth
    0.52
    OutputStream
    0.50
    ?
    0.50
     carb
    0.50
     Jiang
    0.50
    BUT
    0.50
    Activations Density 0.001%

    No Known Activations