© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3260
    Prev
    Next
    INDEX
    Explanations

    xml-like tags and code mixed in sentences

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TypedDataSet
    -0.78
    ftagPool
    -0.66
    /**
    -0.61
    ән
    -0.59
    RegistryLite
    -0.59
    RegressionTest
    -0.58
     disulfide
    -0.57
    artamento
    -0.57
     فريبيس
    -0.57
    ("")]
    -0.56
    POSITIVE LOGITS
     TAMBIÉN
    0.41
    তথ্যসূত্র
    0.41
    intios
    0.36
    TextEditing
    0.35
    latego
    0.35
     ujednoznacz
    0.35
    ✨:
    0.34
     boto
    0.34
    ędziesz
    0.34
    Демографія
    0.34
    Activations Density 6.150%

    No Known Activations