© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150212
    Prev
    Next
    INDEX
    Explanations

    adaptive immunity

    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_18_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
    ใช้
    0.43
    가
    0.42
     You
    0.41
     sử
    0.40
     use
    0.40
    ont
    0.39
    ：
    0.39
     which
    0.38
     you
    0.38
    use
    0.38
    POSITIVE LOGITS
     після
    0.44
    kové
    0.42
     vatth
    0.42
     kebakaran
    0.41
     Selasa
    0.41
    惡
    0.41
    ̒
    0.41
     बोले
    0.40
     پس
    0.40
     malignancies
    0.40
    Activations Density 0.000%

    No Known Activations