© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 13174
    Prev
    Next
    INDEX
    Explanations

    words/phrases indicating association

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
    '}),
    -0.69
    addComponent
    -0.69
    }}},
    -0.68
    ())),
    -0.67
    .*;
    
    -0.66
    nu
    -0.66
    "]);
    -0.65
    ']],
    -0.65
    ']);
    
    -0.63
    "];
    -0.63
    POSITIVE LOGITS
    ^(@)
    0.93
     myſelf
    0.86
    ſelf
    0.85
     Jefus
    0.84
     ainfi
    0.82
     Theſe
    0.81
     themſelves
    0.81
    ſelves
    0.80
     Efq
    0.77
     définiti
    0.77
    Activations Density 3.783%

    No Known Activations