© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12485
    Prev
    Next
    INDEX
    Explanations

    the word "code" and words related to memory regions in code

    oai_token-act-pair · gemini-2.0-flash

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyTitle
    -1.30
     autorytatywna
    -1.26
    AndEndTag
    -1.25
    Geplaatst
    -1.13
     propOrder
    -1.10
    featureID
    -1.09
    IUrlHelper
    -1.07
    __":
    -1.05
    createCanvas
    -1.04
     GenerationType
    -1.03
    POSITIVE LOGITS
    ly
    0.50
    ‑
    0.43
    heid
    0.42
     luce
    0.41
     fact
    0.41
    Factor
    0.41
     risco
    0.40
     risk
    0.40
     fö
    0.40
     significantly
    0.39
    Activations Density 3.049%

    No Known Activations