© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9444
    Prev
    Next
    INDEX
    Explanations

    the word "seat" and related terms

    oai_token-act-pair · gemini-2.0-flash

    seat

    np_max-act · gemini-2.0-flash

    seat

    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
    ſelf
    -1.06
    )");
    -1.01
    ſelves
    -1.01
    $")
    -0.95
    ^(@)
    -0.95
    NUMX
    -0.94
    "},
    -0.91
    ffions
    -0.91
    .";
    -0.90
     ―――――
    -0.90
    POSITIVE LOGITS
    3
    0.61
    2
    0.60
     &
    0.59
    name
    0.59
    9
    0.59
    &
    0.58
    6
    0.58
    ats
    0.57
    est
    0.57
    (&
    0.57
    Activations Density 1.939%

    No Known Activations