Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10038
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code snippets and currency abbreviations

    oai_token-act-pair · gemini-2.0-flash

    words starting with J

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WZ
    -0.49
    Према
    -0.49
     BorderSide
    -0.48
    
    -0.47
    oredCriteria
    -0.46
    ronesia
    -0.45
    urez
    -0.45
     HomeScreen
    -0.44
     Packs
    -0.44
     ***!
    -0.44
    POSITIVE LOGITS
    Joint
    0.85
     Joint
    0.85
     Johnson
    0.84
     joint
    0.81
    Johnson
    0.79
     Jews
    0.79
    JOINT
    0.78
    joint
    0.77
     Jewish
    0.76
     Junior
    0.75
    Activations Density 2.939%

    No Known Activations