© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5246
    Prev
    Next
    INDEX
    Explanations

    improvements

    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_44_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
     dist
    0.43
     covered
    0.43
    盖
    0.43
     Lanz
    0.40
    PLICATIONS
    0.38
     ob
    0.37
    蓋
    0.37
     об
    0.37
    逘
    0.37
    epid
    0.36
    POSITIVE LOGITS
    feature
    0.67
     feature
    0.65
    Feature
    0.63
     ফিচার
    0.63
     Feature
    0.61
     Features
    0.60
     features
    0.59
     fitur
    0.57
    Features
    0.54
     FEATURES
    0.53
    Activations Density 0.006%

    No Known Activations