© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30157
    Prev
    Next
    INDEX
    Explanations

    ranking, position, or place

    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_40_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
    лаб
    0.39
    ndef
    0.37
     फर्स्ट
    0.34
    荫
    0.34
     සම
    0.33
    ionalmente
    0.33
    انوں
    0.33
    addSprite
    0.33
    庵
    0.33
    κών
    0.32
    POSITIVE LOGITS
     place
    1.60
    Place
    1.36
     место
    1.35
    place
    1.27
     Place
    1.27
     lugar
    1.23
     PLACE
    1.17
     miejsce
    1.16
     position
    1.14
     plaats
    1.12
    Activations Density 0.043%

    No Known Activations