© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205410
    Prev
    Next
    INDEX
    Explanations

    statutory

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     hesitation
    0.43
     Point
    0.38
     break
    0.38
     pertinent
    0.37
     point
    0.37
     вид
    0.37
     มอง
    0.37
    活
    0.36
     deliberation
    0.36
     منظور
    0.36
    POSITIVE LOGITS
    强制
    0.41
    䙲
    0.38
     ફર
    0.37
    ConfigFile
    0.37
    彰
    0.37
    Selectors
    0.36
     sectoral
    0.36
    竈
    0.36
    シャレ
    0.36
    スケジュール
    0.35
    Activations Density 0.001%

    No Known Activations