© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    the letter "R" starting a word

    oai_token-act-pair · gemini-2.0-flash

    R

    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
    UnitTesting
    -0.73
    moreland
    -0.67
     Roskov
    -0.62
     AssemblyProduct
    -0.60
    @[+][
    -0.60
    Anlage
    -0.59
     lenker
    -0.58
    canna
    -0.58
    heça
    -0.58
    findpost
    -0.58
    POSITIVE LOGITS
    accoon
    0.53
    honda
    0.51
    amesh
    0.50
     samme
    0.47
     MainAxisSize
    0.46
    oosevelt
    0.46
    itter
    0.45
    IVER
    0.45
    mises
    0.45
    ousse
    0.44
    Activations Density 1.825%

    No Known Activations