© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214644
    Prev
    Next
    INDEX
    Explanations

    Chinese dynasties

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ukh
    0.44
     originated
    0.38
     المثلث
    0.36
    eback
    0.35
    琛
    0.35
    dp
    0.35
     품
    0.35
     drinks
    0.35
     Brigade
    0.34
    Joke
    0.34
    POSITIVE LOGITS
    лах
    0.39
    лизи
    0.37
     বেল
    0.37
     apartamento
    0.37
    얕
    0.37
    醎
    0.37
     erlä
    0.36
    Bue
    0.36
    小白
    0.36
     reag
    0.36
    Activations Density 0.001%

    No Known Activations