© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12496
    Prev
    Next
    INDEX
    Explanations

    code snippets with x, y, point, width, and height variables

    oai_token-act-pair · gemini-2.0-flash

    getX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    adaptiveStyles
    -0.43
     chiaro
    -0.43
     específicas
    -0.43
     fysis
    -0.42
    openzeppelin
    -0.42
     fár
    -0.42
     abito
    -0.42
     specifico
    -0.42
     físicas
    -0.41
     scolaires
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.95
    LookAnd
    0.87
     kaarangay
    0.86
    BeginContext
    0.77
    /**
    0.73
    principalTable
    0.72
    TagMode
    0.69
    ThroughAttribute
    0.65
     виправивши
    0.64
    SequentialGroup
    0.63
    Activations Density 1.106%

    No Known Activations