© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5867
    Prev
    Next
    INDEX
    Explanations

    code license headers

    oai_token-act-pair · gemini-2.0-flash

    software licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    NameInMap
    -0.71
    ftagPool
    -0.69
    GEBURTSDATUM
    -0.65
    MigrationBuilder
    -0.64
     onAnimation
    -0.59
    IndentedString
    -0.59
     Chwiliwch
    -0.57
    matchCondition
    -0.56
    ONYMOUS
    -0.54
     jScrollPane
    -0.54
    POSITIVE LOGITS
     A
    2.66
    A
    2.55
    getA
    1.38
     А
    1.37
    Ａ
    1.32
    А
    1.13
    𝐴
    0.88
    nA
    0.82
    Ⓐ
    0.81
    xA
    0.78
    Activations Density 9.484%

    No Known Activations