© 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. 14872
    Prev
    Next
    INDEX
    Explanations

    words featuring the substring "character" in scientific documents

    oai_token-act-pair · gemini-2.0-flash

    character or minim

    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
    ising
    -0.81
    ised
    -0.75
    isation
    -0.73
    ISED
    -0.73
    IZE
    -0.72
    IZED
    -0.69
    ize
    -0.68
    ise
    -0.66
    ized
    -0.65
    ises
    -0.65
    POSITIVE LOGITS
     highlight
    1.99
     Highlight
    1.88
     highlights
    1.81
     highlighting
    1.74
     highlighted
    1.70
    highlight
    1.70
    Highlight
    1.69
    highlights
    1.68
     Highlights
    1.63
    Highlights
    1.47
    Activations Density 0.796%

    No Known Activations