© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208525
    Prev
    Next
    INDEX
    Explanations

    string sizing or string inverters

    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
     throttle
    0.30
    瀟
    0.27
     although
    0.26
     Gonz
    0.26
     Manifesto
    0.25
     Gonzalez
    0.25
     Thierry
    0.25
     causing
    0.25
     Austrian
    0.25
     maximising
    0.25
    POSITIVE LOGITS
     Topological
    0.26
    琐
    0.25
     ச
    0.24
     ১
    0.23
    рита
    0.23
    盒
    0.23
     fodder
    0.22
     അടു
    0.21
    stdint
    0.21
    ผู้ตัดสิน
    0.21
    Activations Density 0.000%

    No Known Activations