© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8881
    Prev
    Next
    INDEX
    Explanations

    words that seem to connect different parts of phrases or sentences, like prepositions and words that indicate inclusion

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    queryInterface
    -0.68
     betweenstory
    -0.63
    tagHelperRunner
    -0.63
     Infórmanos
    -0.61
    <bos>
    -0.60
     contigo
    -0.59
    ."));
    -0.58
     Biôgrafia
    -0.57
    )"),
    -0.57
    bootstrapcdn
    -0.56
    POSITIVE LOGITS
    terne
    0.53
    >{"
    0.51
    :][
    0.50
     onCreateView
    0.48
    rune
    0.48
    TERN
    0.48
     lẽ
    0.48
     favour
    0.48
    mpa
    0.47
    ilden
    0.47
    Activations Density 2.657%

    No Known Activations