© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43897
    Prev
    Next
    INDEX
    Explanations

    defines parts or processes

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    specific named components or parts within a description.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    en
    0.44
     wrecked
    0.44
    OM
    0.43
     lot
    0.43
     simplifies
    0.43
    v
    0.43
    xico
    0.42
     advertisement
    0.42
    ্ড
    0.42
    ING
    0.42
    POSITIVE LOGITS
     march
    0.55
     marching
    0.54
     newfound
    0.50
     marched
    0.48
     congress
    0.47
     പ്രവര്‍ത്തന
    0.46
     goalie
    0.46
    BagConstraints
    0.46
    mathop
    0.46
    乐
    0.46
    Activations Density 0.000%

    No Known Activations