© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12575
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and cities

    oai_token-act-pair · gemini-2.0-flash

    City

    np_max-act · gemini-2.0-flash

    City

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ^(@)
    -2.14
    BibitemShut
    -1.90
     Efq
    -1.82
     myſelf
    -1.76
    NUMX
    -1.72
    ")));
    -1.70
    >\<^
    -1.70
    $.
    -1.69
     Theſe
    -1.68
     }}$}
    -1.64
    POSITIVE LOGITS
    ↵
    1.59
    ↵↵
    1.44
    1
    1.36
    '
    1.27
    2
    1.27
     
    1.23
    <eos>
    1.20
    3
    1.14
    -
    1.13
    ’
    1.11
    Activations Density 0.568%

    No Known Activations