© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11051
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ranking or comparisons

    oai_token-act-pair · gemini-2.0-flash

    behind or replacing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     lỗi
    -0.46
    対
    -0.37
     tổng
    -0.37
     lead
    -0.36
    潮
    -0.36
    <bos>
    -0.36
    饶
    -0.36
    bes
    -0.36
    せ
    -0.35
    가
    -0.35
    POSITIVE LOGITS
     &___
    0.87
     AssemblyCulture
    0.81
     referenties
    0.81
    principalTable
    0.79
    InputBorder
    0.76
     ProtoMessage
    0.75
    complexContent
    0.74
    AntiForgeryToken
    0.74
    InSection
    0.73
     EconPapers
    0.72
    Activations Density 0.636%

    No Known Activations