© 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. 12550
    Prev
    Next
    INDEX
    Explanations

    a few different letter combinations like "recl", "twi", "kyrm", and medical words having to do with blood flow

    oai_token-act-pair · 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
    lam
    -0.55
    lt
    -0.55
    atan
    -0.54
    len
    -0.54
    lem
    -0.53
    nen
    -0.53
    mam
    -0.52
    IG
    -0.52
    sem
    -0.52
    sie
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.83
     kasarigan
    0.77
     CreateTagHelper
    0.71
     AssemblyCulture
    0.68
    ########.
    0.68
     propOrder
    0.67
     HttpNotFound
    0.64
     pinulongan
    0.64
     resourceCulture
    0.62
     marinho
    0.62
    Activations Density 2.605%

    No Known Activations