© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165310
    Prev
    Next
    INDEX
    Explanations

    Minnesota place names

    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
     geologic
    0.52
     ز
    0.47
     texting
    0.47
     ইত
    0.46
    岁
    0.46
     Бе
    0.46
     méthode
    0.46
    న్నో
    0.46
     éc
    0.46
     funcionalidades
    0.46
    POSITIVE LOGITS
    𝐟
    0.56
    ده
    0.52
    Red
    0.51
    cous
    0.51
    Dus
    0.51
    摑
    0.51
     काटे
    0.50
    dus
    0.50
    dba
    0.49
    Shoes
    0.49
    Activations Density 0.000%

    No Known Activations