© 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. 261180
    Prev
    Next
    INDEX
    Explanations

    Water, expensive, opportunity, Transit, buffer

    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
     gour
    0.44
     الكثير
    0.42
     invariably
    0.41
     многих
    0.40
     العديد
    0.39
     sillonné
    0.39
     domin
    0.38
    哏
    0.38
     zau
    0.38
     многие
    0.38
    POSITIVE LOGITS
     Awards
    0.38
    دیا
    0.38
     ovation
    0.38
    㘟
    0.38
    পুর
    0.37
     Gender
    0.37
    برای
    0.37
    }={
    0.37
     నిర్మాత
    0.37
     Humanities
    0.37
    Activations Density 0.000%

    No Known Activations