© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208100
    Prev
    Next
    INDEX
    Explanations

    online judge, pastebin, exploit-db, drive

    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_20_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
    Antib
    0.22
    /><
    0.21
    Гу
    0.21
    infiltration
    0.21
    Zespół
    0.19
     тази
    0.19
     linearization
    0.19
     inertial
    0.19
    Ми
    0.18
     pristine
    0.18
    POSITIVE LOGITS
    鎸
    0.18
     Worse
    0.17
    κτη
    0.17
    ês
    0.17
     decis
    0.17
     molded
    0.17
    igde
    0.17
    iyet
    0.16
     ενός
    0.16
     his
    0.16
    Activations Density 0.000%

    No Known Activations