© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1931
    Prev
    Next
    INDEX
    Explanations

    religious themes and historical conflicts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.52
    ônus
    -0.50
    netbeans
    -0.49
     وتسجيلات
    -0.45
     IERC
    -0.45
     GridView
    -0.45
     جد
    -0.44
     lạc
    -0.43
     למע
    -0.43
     trifle
    -0.43
    POSITIVE LOGITS
    AndroidJUnit
    0.61
    RequestMethod
    0.61
    XDECREF
    0.59
     MainAxisSize
    0.57
    __(/*!
    0.57
     Roskov
    0.56
    TagMode
    0.55
    VersionUID
    0.54
     pros
    0.52
    |}{}
    0.51
    Activations Density 3.155%

    No Known Activations