© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15997
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for including figures

    oai_token-act-pair · gemini-2.0-flash

    bracket

    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
     Wiktionnaire
    -0.63
    jspx
    -0.63
    PerformLayout
    -0.63
    CROSSTALK
    -0.57
    Erstellt
    -0.50
    XMLSchema
    -0.47
     Parcelable
    -0.47
     plank
    -0.47
    SharedCtor
    -0.47
    RegressionTest
    -0.47
    POSITIVE LOGITS
     Monfieur
    0.64
     auroit
    0.61
     greateſt
    0.56
    WindowConstants
    0.56
     pouvoirs
    0.55
    libft
    0.54
     étoient
    0.54
     فريبيس
    0.52
     démon
    0.52
    сіб
    0.51
    Activations Density 0.503%

    No Known Activations