© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124338
    Prev
    Next
    INDEX
    Explanations

    names of people

    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_37_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
     supre
    0.32
    憾
    0.32
    小学生
    0.31
     horrid
    0.31
    pto
    0.30
     sided
    0.30
     smak
    0.30
     kahe
    0.30
     $€
    0.30
    ght
    0.29
    POSITIVE LOGITS
    StartIndex
    0.31
     كتب
    0.30
     FIV
    0.30
     Indicate
    0.29
    imer
    0.28
    Emb
    0.28
     WANT
    0.28
     Cad
    0.28
     POSSIBLE
    0.28
     понимаю
    0.27
    Activations Density 0.045%

    No Known Activations