© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11903
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to software or programming languages.

    oai_token-act-pair · gemini-2.0-flash

    programming and coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     hänen
    -0.65
     månader
    -0.60
     îna
    -0.59
     legais
    -0.58
     alimentare
    -0.57
     kautta
    -0.56
     esimer
    -0.56
     fraî
    -0.56
     huiles
    -0.55
     timmar
    -0.55
    POSITIVE LOGITS
    WebControls
    0.62
    uests
    0.60
    pstead
    0.58
    infeld
    0.57
    eapple
    0.57
    icorn
    0.57
    HEAST
    0.57
    lsea
    0.57
    drawal
    0.56
    odotus
    0.56
    Activations Density 20.134%

    No Known Activations