© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11501
    Prev
    Next
    INDEX
    Explanations

    words starting with "Embo-" or "Emb-" and sometimes including "Bamb-"

    oai_token-act-pair · gemini-2.0-flash

    Emb

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     GetEnumerator
    -0.68
    findpost
    -0.68
     FontWeight
    -0.66
    sizeCache
    -0.63
    AddTagHelper
    -0.63
    dungen
    -0.60
    __["
    -0.57
     فريبيس
    -0.56
     Undead
    -0.54
    AlterField
    -0.54
    POSITIVE LOGITS
    OCCURRED
    0.48
    '])){
    0.47
     Emb
    0.46
     cuenta
    0.46
    Emb
    0.45
    rowse
    0.45
    half
    0.45
     R
    0.44
    estacks
    0.44
    matum
    0.44
    Activations Density 0.171%

    No Known Activations