© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164429
    Prev
    Next
    INDEX
    Explanations

    illegal sites

    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
     wrists
    0.37
     கிழ
    0.36
     Ank
    0.36
     hood
    0.35
     Arm
    0.35
     vyp
    0.35
     बेह
    0.35
    迋
    0.35
     किलोग्राम
    0.35
     nacionais
    0.35
    POSITIVE LOGITS
    Db
    0.38
    ান্ট
    0.36
    accar
    0.36
    empê
    0.35
    Referências
    0.34
     ብቻ
    0.34
     Zoho
    0.34
     labors
    0.33
    uming
    0.33
    hspace
    0.33
    Activations Density 0.000%

    No Known Activations