© 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. 10524
    Prev
    Next
    INDEX
    Explanations

    the word "eye" and related concepts

    oai_token-act-pair · gemini-2.0-flash

    eye

    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
    Datuak
    -0.60
    enumi
    -0.59
     domanda
    -0.57
    KommentareTeilen
    -0.55
    ★★★★☆
    -0.54
     manos
    -0.52
    士
    -0.49
    الحياه
    -0.48
    +#+
    -0.48
     ivelany
    -0.48
    POSITIVE LOGITS
    +:+
    0.58
    shafen
    0.58
    IntoConstraints
    0.56
    shah
    0.52
    JsonHelper
    0.52
    andaag
    0.50
    @[+][
    0.50
    ischof
    0.48
    makeConstraints
    0.48
     LNB
    0.48
    Activations Density 0.520%

    No Known Activations