© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49476
    Prev
    Next
    INDEX
    Explanations

    fun [descriptor]

    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_10_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
    ס
    0.47
    س
    0.42
    ب
    0.42
    스
    0.38
    {&
    0.37
    
    0.37
    аль
    0.37
    ن
    0.37
    он
    0.36
    клад
    0.36
    POSITIVE LOGITS
    ,
    0.61
    I
    0.45
     sci
    0.44
     g
    0.44
     '
    0.43
     a
    0.42
     movie
    0.40
     so
    0.40
     e
    0.39
     j
    0.39
    Activations Density 0.006%

    No Known Activations