© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13865
    Prev
    Next
    INDEX
    Explanations

    terms related to organic chemistry

    oai_token-act-pair · gemini-2.0-flash

    Lipid bilayers research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ArgsConstructor
    -0.59
     custody
    -0.51
     microfibra
    -0.45
     costumes
    -0.45
     kurtka
    -0.45
     giây
    -0.45
     dispen
    -0.45
     Reichen
    -0.45
     XML
    -0.45
     proposons
    -0.45
    POSITIVE LOGITS
    Broad
    0.70
     Broad
    0.61
     head
    0.61
    CPtr
    0.58
    head
    0.56
    ConstraintMaker
    0.56
     snippetHide
    0.56
    broad
    0.55
    heading
    0.54
     WIDE
    0.54
    Activations Density 2.997%

    No Known Activations