© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51313
    Prev
    Next
    INDEX
    Explanations

    survival games

    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
    umer
    0.37
    гем
    0.36
    formatics
    0.35
     arrowhead
    0.35
    瀹
    0.35
    मेरे
    0.35
    ඌ
    0.35
     Ха
    0.34
    Ian
    0.34
     Дом
    0.33
    POSITIVE LOGITS
     elimin
    0.51
     eliminated
    0.51
     competitors
    0.45
     elimination
    0.45
     eliminación
    0.44
     eliminate
    0.44
    Elim
    0.44
     élim
    0.44
     endurance
    0.43
     contestants
    0.43
    Activations Density 0.066%

    No Known Activations