© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32460
    Prev
    Next
    INDEX
    Explanations

    disruptions or negative outcomes

    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_31_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
     suffered
    0.42
     потер
    0.38
    BibitemShut
    0.37
     vulner
    0.36
     suffers
    0.35
    رځ
    0.35
    க்கமாக
    0.34
    沆
    0.34
     suffer
    0.34
     suffering
    0.34
    POSITIVE LOGITS
     landscape
    0.40
    Log
    0.40
     heure
    0.39
     disrupt
    0.39
     frictions
    0.38
     Landscape
    0.38
    هاء
    0.38
     Hoo
    0.38
    擘
    0.38
     Landschaft
    0.38
    Activations Density 0.042%

    No Known Activations