© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12213
    Prev
    Next
    INDEX
    Explanations

    the apostrophe character

    oai_token-act-pair · gemini-2.0-flash

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     useAuth
    -0.58
    webElementGuid
    -0.56
     дописавши
    -0.54
    ביוגרפיה
    -0.53
    XmlAccessType
    -0.50
     povezave
    -0.50
    Cyfeiriadau
    -0.46
    bop
    -0.43
    wpdb
    -0.43
     dream
    -0.42
    POSITIVE LOGITS
    TagHelper
    0.54
    cheibe
    0.52
     parseFrom
    0.51
     itſelf
    0.50
    ########.
    0.48
    PerformLayout
    0.48
    ADATA
    0.46
    addComponent
    0.46
    advert
    0.45
    клопе
    0.45
    Activations Density 0.201%

    No Known Activations