© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177647
    Prev
    Next
    INDEX
    Explanations

    shopping list

    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_24_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
     تي
    0.41
    бра
    0.41
    fam
    0.39
    漸
    0.39
    רום
    0.38
    டித்த
    0.38
    Thay
    0.37
     tinh
    0.37
    ט
    0.37
     ngon
    0.36
    POSITIVE LOGITS
     extérieure
    0.47
     gallbladder
    0.44
     outbreak
    0.42
     unfinished
    0.41
     submissions
    0.41
     battlefield
    0.41
     adversaries
    0.41
     correspondents
    0.41
     conductors
    0.40
     bodybuilding
    0.40
    Activations Density 0.001%

    No Known Activations