© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91882
    Prev
    Next
    INDEX
    Explanations

    speaking to a group

    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_11_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
    മ
    0.57
     (
    0.56
     December
    0.56
    ส
    0.52
    ")+
    0.51
    基层
    0.51
    Daemon
    0.51
     ()=>
    0.50
    มอ
    0.50
    ம
    0.50
    POSITIVE LOGITS
    Ⲙ
    0.61
    unghi
    0.59
     plats
    0.56
    ó
    0.55
     വ്യത്യ
    0.53
    ﺓ
    0.53
    ulner
    0.52
    ürü
    0.51
    ъз
    0.51
     anuv
    0.51
    Activations Density 0.000%

    No Known Activations