© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2023
    Prev
    Next
    INDEX
    Explanations

    sentences that state the purpose or aim of something

    oai_token-act-pair · gemini-2.0-flash

    goals and intentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    {}/
    -0.59
    {}\
    -0.59
    dataTables
    -0.54
    lysis
    -0.52
    </thead>
    -0.51
    parametrize
    -0.50
    SizeF
    -0.49
    </tfoot>
    -0.49
    */),
    -0.49
     veille
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.79
    ItemBackground
    0.65
    PreferredItem
    0.60
    Gemeinden
    0.59
    AddTagHelper
    0.58
     beginnetje
    0.57
    mapreduce
    0.54
    LayoutStyle
    0.54
     jer
    0.54
    rinfo
    0.53
    Activations Density 1.842%

    No Known Activations