© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14503
    Prev
    Next
    INDEX
    Explanations

    tokens that start with "det", "den", "en", "ny", or "gry"

    oai_token-act-pair · gemini-2.0-flash

    det

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    DropTable
    -0.71
    ſelves
    -0.69
     
    -0.65
     Anſ
    -0.65
     ―――――
    -0.65
    ſelf
    -0.65
     Houſe
    -0.65
    AddTagHelper
    -0.64
     Katrin
    -0.63
     Monfieur
    -0.63
    POSITIVE LOGITS
     /\.
    0.75
     Signalez
    0.63
    áld
    0.56
    nie
    0.54
     He
    0.54
    IGraphics
    0.53
    plast
    0.53
     Paglinawan
    0.53
     You
    0.52
     you
    0.52
    Activations Density 0.023%

    No Known Activations