© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5676
    Prev
    Next
    INDEX
    Explanations

    the word "eye"

    oai_token-act-pair · gemini-2.0-flash

    eye

    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
     eye
    -0.89
     eyew
    -0.65
    eye
    -0.62
     eyes
    -0.61
    Eye
    -0.59
     Eye
    -0.59
     kyse
    -0.55
     ojos
    -0.53
     novios
    -0.53
    s
    -0.52
    POSITIVE LOGITS
    tvguidetime
    1.09
    KommentareTeilen
    0.96
     BoxFit
    0.91
     noDo
    0.83
    CodedInputStream
    0.81
    newswire
    0.81
     мәкалә
    0.80
    IsContent
    0.78
    VideoCapture
    0.78
    awtextra
    0.77
    Activations Density 1.074%

    No Known Activations