© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    political or geographic organizations

    oai_token-act-pair · gemini-2.0-flash

    County-related text

    np_max-act-logits · 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
     county
    -2.25
     County
    -2.16
    County
    -2.11
     COUNTY
    -2.08
    county
    -1.95
    COUNTY
    -1.86
     counties
    -1.83
     Counties
    -1.60
    县
    -1.18
    Sheriff
    -1.12
    POSITIVE LOGITS
    WebElementEntity
    0.53
    الحياه
    0.52
     समीक्षक
    0.49
     Biôgrafia
    0.49
     DbSet
    0.47
    Cyfeiriadau
    0.46
     ext
    0.46
    lgari
    0.46
     ZX
    0.44
    
    0.43
    Activations Density 1.972%

    No Known Activations