© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5879
    Prev
    Next
    INDEX
    Explanations

    mentions of bodily harm, including broken bones, wounds, and injuries.

    oai_token-act-pair · gemini-2.0-flash

    injuries

    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
     protoimpl
    -0.99
    httphttps
    -0.90
     AssemblyProduct
    -0.89
    DockStyle
    -0.88
    findpost
    -0.87
     שוליים
    -0.84
    Diwedd
    -0.83
    LookAnd
    -0.83
     StringTokenizer
    -0.83
    expandindo
    -0.81
    POSITIVE LOGITS
    setzungen
    0.49
     ordf
    0.47
    car
    0.46
     lacri
    0.45
    ocarditis
    0.44
    Big
    0.44
     salivary
    0.42
     nigra
    0.42
     ovary
    0.42
    base
    0.42
    Activations Density 1.388%

    No Known Activations