© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31193
    Prev
    Next
    INDEX
    Explanations

    meet your eyes

    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
    setRoot
    0.36
    堇
    0.34
     علا
    0.34
    yatiti
    0.33
     Slo
    0.33
     enrich
    0.33
    交付
    0.33
    ፦
    0.32
     enriching
    0.32
     ব্রি
    0.31
    POSITIVE LOGITS
    aram
    0.33
    రం
    0.33
     Emerald
    0.32
    emerald
    0.32
    Ꭻ
    0.32
    restrial
    0.32
     સમજ
    0.32
    ધ
    0.32
    ಾರಂಭ
    0.31
    arlama
    0.31
    Activations Density 0.008%

    No Known Activations