© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13188
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to financial transactions or accusations

    oai_token-act-pair · gemini-2.0-flash

    charged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     paying
    -0.84
     Paying
    -0.64
    Paying
    -0.60
    AntiForgeryToken
    -0.58
    paying
    -0.55
    Зноскі
    -0.54
     struggling
    -0.54
     impacted
    -0.53
     experiencing
    -0.51
     suffering
    -0.51
    POSITIVE LOGITS
    AnchorStyles
    0.70
    出版年
    0.60
    AutoScaleMode
    0.59
    ----</
    0.58
    InSection
    0.57
    MethodManager
    0.57
     prou
    0.56
     OFDb
    0.56
     JAXB
    0.55
    orianCalendar
    0.55
    Activations Density 1.122%

    No Known Activations