© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86427
    Prev
    Next
    INDEX
    Explanations

    `@media` queries and keyframes

    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_23_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
     C
    0.45
    z
    0.44
     z
    0.44
      
    0.43
    ycz
    0.39
     A
    0.39
     Rich
    0.39
     Lucky
    0.38
     Z
    0.38
     Here
    0.37
    POSITIVE LOGITS
     overhauled
    0.45
     ஆலோச
    0.44
     reorganized
    0.44
     reorganize
    0.43
     chuy
    0.43
     overse
    0.42
     oversaw
    0.42
     unbel
    0.42
     leves
    0.42
     supernat
    0.42
    Activations Density 0.000%

    No Known Activations