© 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. 13486
    Prev
    Next
    INDEX
    Explanations

    immigration law related language about being in the US.

    oai_token-act-pair · gemini-2.0-flash

    country, nation

    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
    parsedMessage
    -0.79
     متعلقه
    -0.61
    labelledby
    -0.57
    AddTagHelper
    -0.56
     MonoBehaviour
    -0.55
    styleable
    -0.54
    GOTREF
    -0.54
     oprot
    -0.53
    #+#
    -0.52
    ContentAsync
    -0.51
    POSITIVE LOGITS
     country
    2.31
    country
    1.95
     Country
    1.84
    Country
    1.84
     COUNTRY
    1.69
     país
    1.59
    COUNTRY
    1.54
     nation
    1.38
     Paese
    1.34
     страны
    1.24
    Activations Density 1.449%

    No Known Activations