© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5641
    Prev
    Next
    INDEX
    Explanations

    the word "back" and related words, and words related to surfing

    oai_token-act-pair · gemini-2.0-flash

    OCK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    पया
    -0.82
     NSCoder
    -0.81
    ScopeManager
    -0.81
     EconPapers
    -0.75
    principalColumn
    -0.71
    EndProject
    -0.68
    étoit
    -0.67
     pleaſure
    -0.67
    Exposition
    -0.66
     saurait
    -0.66
    POSITIVE LOGITS
     label
    0.47
    ude
    0.43
     success
    0.41
    setBorder
    0.40
    label
    0.39
     light
    0.39
    bo
    0.39
    <h6>
    0.39
    bitField
    0.39
     kotlinx
    0.38
    Activations Density 1.801%

    No Known Activations