© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8021
    Prev
    Next
    INDEX
    Explanations

    the word "you" and terms ending in "ley", and when "recently" is used

    oai_token-act-pair · gemini-2.0-flash

    ley

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    if
    -1.24
    I
    -1.17
    _
    -1.14
    H
    -1.13
    P
    -1.12
    u
    -1.11
    h
    -1.10
    un
    -1.09
    we
    -1.08
    p
    -1.08
    POSITIVE LOGITS
    NUMX
    1.59
    ]--;
    1.56
    '],
    
    1.55
    )";
    
    1.55
    ratulations
    1.53
    )");
    
    1.52
    "],
    
    1.48
    BibitemShut
    1.48
    "):
    
    1.48
    ')):
    1.48
    Activations Density 1.414%

    No Known Activations