© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5325
    Prev
    Next
    INDEX
    Explanations

    mentions of times along with "a.m." and "p.m." and also "time zones"

    oai_token-act-pair · gemini-2.0-flash

    geographical directions related to the west

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

    West

    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
     виправивши
    -0.74
    ChildScrollView
    -0.67
     دیکھیے
    -0.66
     ivelany
    -0.65
    IVEREF
    -0.59
    IntoConstraints
    -0.58
    anInt
    -0.55
    ConstraintMaker
    -0.55
     gynhyrchwyd
    -0.54
     ProtoMessage
    -0.54
    POSITIVE LOGITS
     West
    1.13
     Western
    1.05
    West
    1.01
     western
    1.00
    west
    0.96
    western
    0.94
     west
    0.94
    Western
    0.93
     WEST
    0.90
    Ouest
    0.86
    Activations Density 1.379%

    No Known Activations