© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    angle brackets related to formatting or code and javascript code

    oai_token-act-pair · gemini-2.0-flash

    computer markup

    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
     дописавши
    -1.10
    elemField
    -0.84
    XmlAccessType
    -0.78
    EDEFAULT
    -0.77
    ngdoc
    -0.75
     <>",
    -0.75
    EndProject
    -0.74
    OGND
    -0.74
     مشين
    -0.70
     betweenstory
    -0.69
    POSITIVE LOGITS
    quei
    0.43
     fals
    0.42
    WE
    0.41
    herbe
    0.39
     yet
    0.38
     calibration
    0.38
     obsah
    0.37
     contents
    0.37
    yet
    0.37
     запо
    0.36
    Activations Density 0.680%

    No Known Activations