© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4826
    Prev
    Next
    INDEX
    Explanations

    common words that serve a grammatical function.

    oai_token-act-pair · gemini-2.0-flash

    Closing parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    </h4>
    -0.99
     (
    -0.77
    ::_('
    -0.70
    （
    -0.61
     auroit
    -0.54
     vermelhas
    -0.53
    省市镇
    -0.52
    (
    -0.51
    脚注の使い方
    -0.51
    berdayakan
    -0.51
    POSITIVE LOGITS
    ),
    1.91
    )
    1.84
    )
    1.73
    )),
    1.66
    ),"
    1.64
    ),”
    1.63
    !),
    1.62
    ):
    1.62
    ?),
    1.61
    )',
    1.60
    Activations Density 30.551%

    No Known Activations