© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1643
    Prev
    Next
    INDEX
    Explanations

    strings containing 'x' and numbers

    oai_token-act-pair · gemini-2.0-flash

    code addresses

    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
     binary
    -0.69
     pleaſure
    -0.69
     pinulongan
    -0.69
     reaſon
    -0.65
    binary
    -0.65
     auffi
    -0.64
    MessageTagHelper
    -0.63
     poffible
    -0.62
     hexadecimal
    -0.60
     Binary
    -0.60
    POSITIVE LOGITS
    TRIBUN
    0.57
    cock
    0.52
     fac
    0.49
    atorio
    0.47
     tour
    0.46
     Franz
    0.44
    EAN
    0.44
     url
    0.44
    openqa
    0.44
     web
    0.43
    Activations Density 2.222%

    No Known Activations