© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44203
    Prev
    Next
    INDEX
    Explanations

    Hezbollah or mites

    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
     relatos
    0.16
    䍩
    0.15
    倞
    0.14
     yal
    0.14
     cuyas
    0.13
     diversas
    0.13
     Segundo
    0.13
     técnico
    0.13
     ಇದರ
    0.13
     Queste
    0.13
    POSITIVE LOGITS
    p
    0.15
    ARE
    0.14
    are
    0.13
    w
    0.13
    。)
    0.12
     btw
    0.12
     thickened
    0.12
    x
    0.12
    pane
    0.12
    Thickness
    0.12
    Activations Density 0.001%

    No Known Activations