© 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. 15945
    Prev
    Next
    INDEX
    Explanations

    no matter

    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
    thing
    0.49
    ithing
    0.46
    BODY
    0.46
     herein
    0.46
     way
    0.46
     semblance
    0.45
    ෝ
    0.43
    here
    0.43
    THING
    0.42
    HERE
    0.41
    POSITIVE LOGITS
    `.
    0.42
    `;
    0.40
    ```
    0.38
    `,
    0.37
    ਜ਼
    0.34
    byterian
    0.34
     `--
    0.33
     `
    0.33
    üss
    0.33
    `:
    0.33
    Activations Density 0.018%

    No Known Activations