© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43889
    Prev
    Next
    INDEX
    Explanations

    directly incorporated/inserted/into

    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_22_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
     sizz
    0.22
    صف
    0.20
    Soft
    0.20
     scre
    0.20
     gains
    0.20
     leader
    0.19
    録
    0.19
     CRA
    0.19
     remember
    0.19
    DA
    0.19
    POSITIVE LOGITS
    reproductive
    0.20
     Reproductive
    0.20
    ongyang
    0.20
    ောက်ပ
    0.19
    แกรม
    0.19
     ዓይነት
    0.19
    ᕆ
    0.19
     tramite
    0.18
     एलर्जी
    0.18
     carcinogenesis
    0.18
    Activations Density 0.018%

    No Known Activations