© 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. 15012
    Prev
    Next
    INDEX
    Explanations

    articles, numbers and words indicating singularity or small quantities

    oai_token-act-pair · gemini-2.0-flash

    single

    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
     FetchType
    -0.83
    adpleegd
    -0.82
    Obrázky
    -0.75
     Houſe
    -0.73
     ſche
    -0.72
     Theſe
    -0.71
    ScopeManager
    -0.71
    XmlAccessorType
    -0.71
    abestanden
    -0.71
    ंदीखरीदारी
    -0.70
    POSITIVE LOGITS
     single
    4.00
    single
    3.63
     Single
    3.33
    Single
    3.31
     SINGLE
    3.09
    SINGLE
    2.75
     singles
    2.16
    单
    2.16
     singolo
    2.05
    單
    1.90
    Activations Density 2.489%

    No Known Activations