© 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. 6192
    Prev
    Next
    INDEX
    Explanations

    HTML code for references, especially including the span tag to find authors

    oai_token-act-pair · gemini-2.0-flash

    span

    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
    ati
    -0.41
    ци
    -0.41
     
    -0.40
     furthermore
    -0.39
    ми
    -0.39
    cout
    -0.38
    ru
    -0.38
     Hash
    -0.37
     Clock
    -0.37
    ти
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    1.05
     betweenstory
    0.82
     AssemblyTitle
    0.81
    InjectAttribute
    0.81
    elemField
    0.78
     للاسماء
    0.77
     EconPapers
    0.77
    曖昧さ回避
    0.76
    expandindo
    0.76
    LookAnd
    0.76
    Activations Density 0.215%

    No Known Activations