© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241698
    Prev
    Next
    INDEX
    Explanations

    no single answer

    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_40_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
     hanya
    0.42
     everyone
    0.42
     only
    0.40
     只
    0.40
    <unused33>
    0.39
    Everyone
    0.38
    只
    0.38
     iedereen
    0.37
     Only
    0.37
     csak
    0.37
    POSITIVE LOGITS
     मर्ज
    0.39
     Daw
    0.36
     ਰ
    0.36
     suficientes
    0.36
     پوس
    0.36
    lym
    0.35
     충분
    0.35
     one
    0.34
     நிர்வாக
    0.34
     respectable
    0.34
    Activations Density 0.010%

    No Known Activations