© 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. 12111
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to documentation of information, trips and death

    oai_token-act-pair · 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
    /$',
    -0.63
    rateful
    -0.57
    )”
    -0.57
    ')")
    -0.57
    )»
    -0.57
    %</
    -0.56
    hatic
    -0.56
    ]),
    -0.55
    %$$
    -0.54
    ']],
    -0.54
    POSITIVE LOGITS
     Porém
    0.68
     Monfieur
    0.66
     houſe
    0.66
     himſelf
    0.61
     Theſe
    0.61
     myſelf
    0.60
     poffe
    0.60
     Reſ
    0.59
     للمعارف
    0.59
     Tuttavia
    0.59
    Activations Density 2.489%

    No Known Activations