© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101541
    Prev
    Next
    INDEX
    Explanations

    Helios, Elite Four, Island, ing

    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_14_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
     a
    0.54
     del
    0.53
    o
    0.51
     beggars
    0.50
     S
    0.49
     gelatin
    0.46
     hump
    0.46
     Mehmet
    0.46
    ాయి
    0.46
     Catalan
    0.46
    POSITIVE LOGITS
     作为
    0.61
     Datensch
    0.54
    ૩
    0.54
     потен
    0.53
     га
    0.52
     እንቅ
    0.51
    ）,
    0.51
     часу
    0.51
     тщательно
    0.51
     сі
    0.50
    Activations Density 0.000%

    No Known Activations