© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153268
    Prev
    Next
    INDEX
    Explanations

    optics terms: mirror, lens, droplet

    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
     Domin
    0.41
    lichting
    0.38
    ियर
    0.38
     many
    0.37
     announced
    0.36
     Jansen
    0.36
     mitig
    0.35
    )}
    0.35
     numerose
    0.35
     shortly
    0.35
    POSITIVE LOGITS
     cesium
    0.46
    泻
    0.43
    腺
    0.43
    onycha
    0.40
    瀉
    0.40
     religions
    0.40
    atinib
    0.39
    穿着
    0.39
     intrav
    0.38
     расположен
    0.38
    Activations Density 0.001%

    No Known Activations