© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9918
    Prev
    Next
    INDEX
    Explanations

    Use Case Actors

    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_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
     freshness
    0.15
    Aph
    0.15
     देयर
    0.14
    \%)
    0.14
     %)
    0.14
     intelligible
    0.14
    Lots
    0.14
     carinatis
    0.14
    ριά
    0.14
     lymphatiques
    0.14
    POSITIVE LOGITS
     Durante
    0.17
    ↵↵
    0.16
    </h3>
    0.16
     shareholders
    0.16
     לא
    0.16
    শিকান্ত
    0.15
     prosecutors
    0.15
     Raiders
    0.15
     Toronto
    0.15
     dejan
    0.14
    Activations Density 0.018%

    No Known Activations