© 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. 10000
    Prev
    Next
    INDEX
    Explanations

    what appear to be disparate words and letter combinations.

    oai_token-act-pair · gemini-2.0-flash

    doll

    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
    nav
    -0.65
     LEV
    -0.64
     Tav
    -0.64
    Tav
    -0.63
     Prow
    -0.62
    ROV
    -0.60
     Tev
    -0.60
    taw
    -0.60
    gow
    -0.59
     Bew
    -0.59
    POSITIVE LOGITS
    Wp
    0.69
    epam
    0.66
     Hooper
    0.66
    Vp
    0.65
     Wp
    0.64
     sop
    0.63
    CPtr
    0.63
     Coppola
    0.63
    topp
    0.63
    oppa
    0.62
    Activations Density 4.183%

    No Known Activations