© 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. 15571
    Prev
    Next
    INDEX
    Explanations

    organization memberships

    oai_token-act-pair · gemini-2.0-flash

    Sewing and crafting

    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
     المعيارى
    -0.65
    iastical
    -0.64
    TRIBUTE
    -0.63
     HttpNotFound
    -0.59
    DoubleQuotes
    -0.58
    CppMethod
    -0.57
    løs
    -0.57
     onOptions
    -0.57
     tslint
    -0.56
     onAnimation
    -0.55
    POSITIVE LOGITS
    Models
    0.56
    IndentedString
    0.56
    sor
    0.49
     referenties
    0.48
    models
    0.47
    resave
    0.47
     CURIAM
    0.47
    Chham
    0.46
    TargetApi
    0.46
    intahan
    0.45
    Activations Density 1.170%

    No Known Activations