© 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. 132899
    Prev
    Next
    INDEX
    Explanations

    formatting marks

    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
     বলিব
    0.38
    Harrison
    0.37
     Harrison
    0.37
    =$(
    0.37
     Madd
    0.36
    ствие
    0.36
    也不会
    0.35
     bl
    0.35
     ਦੀ
    0.35
     Poisson
    0.35
    POSITIVE LOGITS
    Bounce
    0.43
     Formatting
    0.41
     compt
    0.40
    āo
    0.40
    改
    0.39
     Sequencing
    0.38
     criticisms
    0.38
    omal
    0.37
    SOUTH
    0.37
    boe
    0.36
    Activations Density 0.001%

    No Known Activations