© 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. 15553
    Prev
    Next
    INDEX
    Explanations

    technical, often legal or political, discussions

    oai_token-act-pair · 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
     AssemblyCulture
    -0.93
    FunctionFlags
    -0.78
    ImageContext
    -0.74
    MethodManager
    -0.68
    stdc
    -0.67
    AnchorStyles
    -0.64
     nahilalakip
    -0.64
     MainAxisSize
    -0.63
    makeConstraints
    -0.61
    resave
    -0.60
    POSITIVE LOGITS
     متعلقه
    0.55
     Haarlem
    0.55
    ARTA
    0.47
    alamus
    0.46
     tranquilidad
    0.46
    ]-->
    0.45
     magasiner
    0.44
    řeba
    0.44
    trino
    0.43
    busy
    0.42
    Activations Density 16.661%

    No Known Activations