© 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. 9941
    Prev
    Next
    INDEX
    Explanations

    figure and table references within scientific or legal documents

    oai_token-act-pair · gemini-2.0-flash

    research papers and figures

    np_max-act · 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
     Theſe
    -0.49
    Erreferentziak
    -0.49
    OrNil
    -0.47
    teilungen
    -0.46
    rdf
    -0.46
    virons
    -0.45
    yii
    -0.45
    ideration
    -0.43
     palk
    -0.42
    cellaneous
    -0.42
    POSITIVE LOGITS
     typelib
    0.63
    tvguidetime
    0.62
    DockStyle
    0.55
    
    0.54
    <bos>
    0.54
    FormTagHelper
    0.53
    tanooga
    0.52
    :✨
    0.52
    oprot
    0.51
     betweenstory
    0.51
    Activations Density 2.900%

    No Known Activations