© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200967
    Prev
    Next
    INDEX
    Explanations

    higashi and port road

    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_12_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
    ਨ
    0.12
    čen
    0.12
     overcoming
    0.11
     lexical
    0.11
    čkog
    0.11
     malice
    0.11
    ccgi
    0.11
    herent
    0.11
    න
    0.11
    rac
    0.11
    POSITIVE LOGITS
    ```
    0.15
    l
    0.15
     Võ
    0.14
    s
    0.12
    IT
    0.12
    AL
    0.12
    i
    0.12
    鍝
    0.12
    g
    0.12
    TER
    0.11
    Activations Density 0.001%

    No Known Activations