© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44561
    Prev
    Next
    INDEX
    Explanations

    common areas or tourist areas

    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_22_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
     فشاں
    0.44
     endet
    0.42
     Karite
    0.41
     میشه
    0.41
    рида
    0.41
    DIV
    0.40
    هایت
    0.40
    滞
    0.40
     امتحان
    0.39
     初
    0.39
    POSITIVE LOGITS
     Old
    0.52
     concerning
    0.47
     only
    0.43
     seats
    0.43
     बाई
    0.43
     considering
    0.43
     Jews
    0.41
     administering
    0.41
     oligarch
    0.41
     constructors
    0.41
    Activations Density 0.001%

    No Known Activations