© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240816
    Prev
    Next
    INDEX
    Explanations

    gaming performance

    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_25_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
    ')]
    0.34
    യാണ്
    0.32
    til
    0.31
     Vikt
    0.31
    romy
    0.31
     ঠাকুরের
    0.31
    ni
    0.30
     området
    0.30
     Pion
    0.30
    ')])
    0.30
    POSITIVE LOGITS
     compare
    0.35
     compl
    0.34
     Compare
    0.32
     rẻ
    0.32
     נא
    0.31
     comparative
    0.31
     blitz
    0.31
     criticize
    0.30
    метка
    0.30
     ליי
    0.30
    Activations Density 0.009%

    No Known Activations