© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6857
    Prev
    Next
    INDEX
    Explanations

    Objective-C code related to UI elements and numerical values

    oai_token-act-pair · gemini-2.0-flash

    terms related to data types and numbers

    np_token-act-pair-logits · gpt-4o-mini

    double precision numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     int
    -1.30
     Int
    -1.15
    int
    -1.13
     INT
    -1.08
    Int
    -1.05
     integer
    -1.03
     ints
    -0.95
    INT
    -0.95
     Integer
    -0.94
     Inte
    -0.93
    POSITIVE LOGITS
     double
    0.83
    double
    0.75
     numbers
    0.69
     Double
    0.67
     doble
    0.64
    Double
    0.61
    DOUBLE
    0.60
    numbers
    0.59
     Number
    0.59
     dubbel
    0.57
    Activations Density 2.045%

    No Known Activations