© 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. 12252
    Prev
    Next
    INDEX
    Explanations

    hedging phrases like "just about," "virtually," "almost," and "nearly."

    oai_token-act-pair · gemini-2.0-flash

    Lack of quantity

    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
    __*/
    -0.80
     препратки
    -0.75
    mybatisplus
    -0.75
     nahilalakip
    -0.71
    webElementXpaths
    -0.68
     disambiguazione
    -0.68
    цезда
    -0.66
    GEBURTSDATUM
    -0.65
     &___
    -0.65
    RegistryLite
    -0.65
    POSITIVE LOGITS
     none
    1.59
    none
    1.55
    None
    1.41
     any
    1.34
     None
    1.34
     anyone
    1.20
    NONE
    1.20
     ninguno
    1.19
     everyone
    1.18
    any
    1.17
    Activations Density 0.830%

    No Known Activations