© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2723
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers, potentially references or footnotes within legal documents

    oai_token-act-pair · gemini-2.0-flash

    [

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     thing
    -2.69
     THING
    -2.16
     Thing
    -2.06
    thing
    -1.98
    Thing
    -1.98
     things
    -1.84
     Things
    -1.73
    Things
    -1.66
     THINGS
    -1.59
    things
    -1.55
    POSITIVE LOGITS
    5
    0.45
    3
    0.45
    4
    0.45
    7
    0.42
    6
    0.40
    8
    0.40
     dozens
    0.39
     getopt
    0.38
    íficos
    0.38
    9
    0.38
    Activations Density 3.697%

    No Known Activations