© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34818
    Prev
    Next
    INDEX
    Explanations

    lesson duration and absence

    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_31_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
    思
    0.32
     தங்க
    0.32
    iby
    0.31
    Ւ
    0.31
    迷惑
    0.31
    {}
    0.31
     distressing
    0.31
    ﾚ
    0.31
    nan
    0.30
    Diego
    0.30
    POSITIVE LOGITS
     NLP
    0.43
    の時間
    0.39
    chedules
    0.39
     पुस्त
    0.38
    NLP
    0.38
     Schedules
    0.38
     Luther
    0.36
     Epidemiology
    0.36
    Luther
    0.36
    Administrative
    0.35
    Activations Density 0.002%

    No Known Activations