© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7769
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to incremental progress

    oai_token-act-pair · gemini-2.0-flash

    step

    np_max-act-logits · gemini-2.0-flash

    terms related to procedural steps

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.85
     '\\;'
    -0.72
    ^(@)
    -0.71
    PerformLayout
    -0.67
    MessageTagHelper
    -0.64
    "],
    -0.63
     saites
    -0.63
    Przypisy
    -0.60
     ComVisible
    -0.59
     MaterialApp
    -0.59
    POSITIVE LOGITS
     soit
    0.50
    迅
    0.49
    <thead>
    0.46
    例文帳に追加
    0.46
    ;#
    0.46
     rius
    0.44
     Alistair
    0.43
     ujednoznacz
    0.43
     transfieras
    0.43
     indietro
    0.42
    Activations Density 9.958%

    No Known Activations