© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43725
    Prev
    Next
    INDEX
    Explanations

    Scott, Tim, Southorcommunity, lodge, commonwealth

    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_13_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
     With
    0.56
    },
    0.53
    With
    0.51
    ئ
    0.51
    但
    0.51
     with
    0.49
    沈
    0.49
    <0x0D>
    0.48
    ',
    0.48
     Bertrand
    0.48
    POSITIVE LOGITS
    eleaf
    0.61
     sAlarm
    0.57
     сложных
    0.57
     یخچال
    0.55
     inlay
    0.54
    StarGo
    0.53
     IPTV
    0.53
     inspiración
    0.53
     pavers
    0.53
     chipset
    0.53
    Activations Density 0.000%

    No Known Activations