© 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. 5509
    Prev
    Next
    INDEX
    Explanations

    the word "data" and words associated with studies

    oai_token-act-pair · gemini-2.0-flash

    data

    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
    webElementXpaths
    -0.79
     Roskov
    -0.71
     ویکی‌پدی
    -0.69
     betweenstory
    -0.65
     purpoſe
    -0.65
    #+#
    -0.64
    OGND
    -0.63
    цездатний
    -0.63
     "..\..\
    -0.61
    esez
    -0.60
    POSITIVE LOGITS
    spender
    0.45
    NgModule
    0.44
     Merdeka
    0.43
     있어
    0.41
    urangi
    0.39
    TestingModule
    0.39
    JScrollPane
    0.39
     contra
    0.39
    RegressionTest
    0.39
    owanym
    0.39
    Activations Density 4.702%

    No Known Activations