© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204282
    Prev
    Next
    INDEX
    Explanations

    // -----------------------------------------------------------------------------

    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_25_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
     Zachary
    0.25
    はい
    0.24
     Fabric
    0.24
     prepare
    0.24
     দেখেন
    0.24
    ?
    0.23
     Mathe
    0.23
     Bul
    0.23
     Hawk
    0.23
     Bulb
    0.23
    POSITIVE LOGITS
    针
    0.33
     needle
    0.28
    needle
    0.27
    قیق
    0.27
    pooled
    0.26
     adquisición
    0.25
     aquell
    0.25
     aquilo
    0.25
     cij
    0.25
     silic
    0.24
    Activations Density 0.000%

    No Known Activations