© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by numbers or 'A'

    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_39_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
     contending
    0.39
    mnemonic
    0.38
    ᱭ
    0.38
    मेन
    0.38
     meng
    0.38
     मंजूर
    0.38
     Menzies
    0.38
     contended
    0.37
    fungsi
    0.37
    oxymethyl
    0.37
    POSITIVE LOGITS
     III
    0.44
     II
    0.41
    Pages
    0.40
    III
    0.39
     A
    0.39
    Adam
    0.38
     iii
    0.37
     Supplements
    0.37
     G
    0.37
    ิ่ง
    0.37
    Activations Density 0.024%

    No Known Activations