© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4128
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially code involving arrays, bracketed numbers, and variables

    oai_token-act-pair · gemini-2.0-flash

    say "1 or 0"

    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
    InputTagHelper
    -0.66
    fjspx
    -0.62
    Datuak
    -0.60
    ImageContext
    -0.60
     zeros
    -0.60
    UnknownFieldSet
    -0.59
    OGND
    -0.59
     zeroes
    -0.58
     zero
    -0.57
     تضيفلها
    -0.57
    POSITIVE LOGITS
    1
    0.63
     First
    0.58
    First
    0.57
    FIRST
    0.54
     first
    0.52
    １
    0.52
    ViewPager
    0.52
    first
    0.50
     članak
    0.50
     erste
    0.49
    Activations Density 2.028%

    No Known Activations