© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7528
    Prev
    Next
    INDEX
    Explanations

    strings of words that resemble an argument

    oai_token-act-pair · gemini-2.0-flash

    apply

    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
    vallis
    -0.58
    +#+
    -0.57
    eseorang
    -0.53
     dispozici
    -0.52
    NOPQRST
    -0.50
    Демографія
    -0.50
    ấc
    -0.49
    toyage
    -0.48
    ьаж
    -0.48
     MonoBehaviour
    -0.47
    POSITIVE LOGITS
     application
    2.58
    application
    2.31
     Application
    2.19
     applied
    2.16
     apply
    2.14
     applying
    2.13
    Application
    2.11
     applications
    1.97
    apply
    1.95
     APPLICATION
    1.95
    Activations Density 3.189%

    No Known Activations