© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214516
    Prev
    Next
    INDEX
    Explanations

    list/code formatting

    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_50_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
     mettant
    0.44
    遄
    0.43
    கிர
    0.43
    ᅩ
    0.43
    Те
    0.43
    روں
    0.43
     ریک
    0.43
    tAux
    0.42
     deuteron
    0.42
    逘
    0.42
    POSITIVE LOGITS
    right
    0.44
     S
    0.41
     right
    0.41
    qu
    0.40
    quality
    0.37
    ким
    0.37
     Kim
    0.36
      
    0.36
     quality
    0.36
    soft
    0.35
    Activations Density 0.000%

    No Known Activations