© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 260692
    Prev
    Next
    INDEX
    Explanations

    examples of tables

    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
    '}}>
    0.28
    ība
    0.28
    до
    0.27
     '>'
    0.27
    "}}>
    0.27
    сү
    0.27
     Hiring
    0.27
     gourd
    0.27
    ອ
    0.27
    ığını
    0.26
    POSITIVE LOGITS
     memperhatikan
    0.24
     وهكذا
    0.24
    decreasing
    0.23
    hydrox
    0.22
     každ
    0.22
     رود
    0.22
     comprehensive
    0.22
     جنب
    0.22
     بعض
    0.22
     össz
    0.22
    Activations Density 0.000%

    No Known Activations