© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6063
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of numerical data

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    ChildScrollView
    -1.32
     الحره
    -1.23
    BeginContext
    -1.19
    SharedCtor
    -1.18
    ContentAsync
    -1.16
     متعلقه
    -1.14
     يتيمه
    -1.13
    ConstraintMaker
    -1.13
    __':
    -1.13
     ExecuteAsync
    -1.08
    POSITIVE LOGITS
    ,
    0.79
     o
    0.49
    1
    0.47
    <eos>
    0.47
    -
    0.46
    M
    0.46
    2
    0.45
    ↵↵
    0.44
    B
    0.44
    ha
    0.44
    Activations Density 4.313%

    No Known Activations