© 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. 31819
    Prev
    Next
    INDEX
    Explanations

    validation success or failure

    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
    
    0.41
    teau
    0.40
    鲛
    0.40
    strong
    0.39
    िएको
    0.39
    sul
    0.38
     Zul
    0.38
    .°
    0.38
    ෝග
    0.38
     ",",
    0.38
    POSITIVE LOGITS
     Epilepsy
    0.40
     EP
    0.40
     MSP
    0.39
    ब्रा
    0.38
     epilepsy
    0.38
     m
    0.38
     im
    0.36
     IM
    0.35
    嵋
    0.35
     View
    0.35
    Activations Density 0.001%

    No Known Activations