© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    npm commands: install, start, create

    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
    ẵ
    0.36
     Trig
    0.36
     Co
    0.35
    apartment
    0.35
     Base
    0.35
     Zo
    0.35
    े
    0.34
     apar
    0.34
     apartamento
    0.34
    ỹ
    0.34
    POSITIVE LOGITS
    잍
    0.39
    䋇
    0.38
     ဒ
    0.37
    など
    0.37
     Livraison
    0.37
     फ
    0.37
     최대
    0.36
     связано
    0.36
    prochen
    0.35
    ৪৩
    0.35
    Activations Density 0.039%

    No Known Activations