© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209025
    Prev
    Next
    INDEX
    Explanations

    positional encoding

    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_20_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
    mechanism
    0.19
     mechanism
    0.19
    ライブ
    0.18
    твор
    0.18
    "][
    0.18
    غي
    0.18
    съ
    0.18
    determination
    0.18
     brawl
    0.18
     formations
    0.18
    POSITIVE LOGITS
    わせて
    0.21
    或者
    0.19
    maier
    0.19
     Clone
    0.18
     Together
    0.18
     Yamaha
    0.18
     reprendre
    0.18
     Replace
    0.18
     jakarta
    0.18
    }),
    0.18
    Activations Density 0.003%

    No Known Activations