© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7302
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    programming syntax

    np_token-act-pair-logits · gpt-4o-mini

    say "date separators"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ProtoMessage
    -0.93
    jspx
    -0.77
    InteropServices
    -0.71
    StoryboardSegue
    -0.71
    SharedDtor
    -0.69
     فريبيس
    -0.67
     CreateTagHelper
    -0.66
    fillType
    -0.62
    abestanden
    -0.61
    ChildIndex
    -0.61
    POSITIVE LOGITS
    Abp
    0.51
     Drapeau
    0.48
     historique
    0.42
     ){
    0.42
     Meters
    0.40
     við
    0.40
    :]:
    0.39
     Egli
    0.39
     raiſ
    0.39
     stay
    0.38
    Activations Density 2.148%

    No Known Activations