© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16012
    Prev
    Next
    INDEX
    Explanations

    fragments of computer code or text about scientific values and reporting

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Laver
    -0.48
     Mer
    -0.48
     nor
    -0.47
    ordes
    -0.46
    を紹介します
    -0.45
     fure
    -0.45
     candidate
    -0.44
     fu
    -0.43
    '&:
    -0.43
    CHAM
    -0.42
    POSITIVE LOGITS
    AsUp
    0.77
     ExecuteAsync
    0.76
    ValueStyle
    0.70
    IGraphics
    0.68
    badlogic
    0.68
    bootstrapcdn
    0.65
    )_/¯
    0.65
    omitempty
    0.64
     Paglinawan
    0.64
     pageContext
    0.63
    Activations Density 13.993%

    No Known Activations