© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3249
    Prev
    Next
    INDEX
    Explanations

    code comments and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ه
    1.23
    های
    1.22
    sters
    1.15
    هایی
    1.01
    er
    1.00
    ad
    0.95
    ﻚ
    0.94
    s
    0.94
    un
    0.93
    Warning
    0.92
    POSITIVE LOGITS
     isotherms
    1.13
     semblance
    1.12
     darn
    1.04
    рби
    1.00
     કરાવ
    0.98
     damn
    0.98
    仮
    0.96
     drog
    0.95
    もの
    0.95
     overd
    0.95
    Activations Density 0.057%

    No Known Activations