© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68235
    Prev
    Next
    INDEX
    Explanations

    intelligence or smartness

    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_46_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
     papi
    0.36
     sublicense
    0.34
     Jahrhundert
    0.34
    ்க்க
    0.33
    ṑ
    0.33
    轧
    0.32
    veer
    0.32
    逸
    0.32
    줍
    0.32
     Ecusson
    0.32
    POSITIVE LOGITS
    智能
    2.44
     intelligent
    2.41
     smart
    2.39
     inteligente
    2.25
     Intelligent
    2.13
     intelligente
    2.13
    smart
    2.11
    Smart
    2.11
     inteligentes
    2.11
    intelligent
    2.11
    Activations Density 0.294%

    No Known Activations