© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10037
    Prev
    Next
    INDEX
    Explanations

    mentions of video gaming and crafting

    oai_token-act-pair · gemini-2.0-flash

    equip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Diweddarwch
    -0.60
     CreateTagHelper
    -0.57
    󠁢
    -0.56
    oneofs
    -0.56
     doInBackground
    -0.54
    IsMutable
    -0.54
    StructEnd
    -0.53
    ToBounds
    -0.53
     دیکھیے
    -0.53
    TestBed
    -0.52
    POSITIVE LOGITS
     equipped
    0.77
     Audiodateien
    0.75
     equip
    0.75
     Equip
    0.71
    equipped
    0.68
    Equipped
    0.65
     equipping
    0.65
    equip
    0.65
     interaction
    0.65
     equi
    0.65
    Activations Density 3.022%

    No Known Activations