© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153641
    Prev
    Next
    INDEX
    Explanations

    High Proficiency, Immediately

    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_23_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
     فيدي
    0.34
    ತು
    0.33
     transitioned
    0.32
     કર્
    0.32
     arenas
    0.32
    摻
    0.32
     transición
    0.32
    摑
    0.32
    ござ
    0.31
     SmackDown
    0.31
    POSITIVE LOGITS
    pr
    0.35
    midd
    0.33
    放射
    0.33
    光
    0.33
    including
    0.32
    不足
    0.32
    粎
    0.32
    aky
    0.32
     ny
    0.31
    included
    0.31
    Activations Density 0.029%

    No Known Activations