© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205642
    Prev
    Next
    INDEX
    Explanations

    assignments of variables like `a=1`, `b=4`

    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_25_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
    ificent
    0.37
    Medit
    0.36
    ival
    0.35
     تحد
    0.34
    ヾ
    0.33
    ifs
    0.33
     hayan
    0.33
     Uptown
    0.33
     गुजरात
    0.33
    愤
    0.33
    POSITIVE LOGITS
     spreadsheet
    0.41
     soil
    0.39
    ほぼ
    0.38
     spreadsheets
    0.38
     Normalize
    0.37
     셀
    0.36
     거의
    0.36
     sheets
    0.35
    rien
    0.35
     plant
    0.34
    Activations Density 0.001%

    No Known Activations