© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15527
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology

    oai_token-act-pair · gemini-2.0-flash

    cause-and-effect relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ainfi
    -0.80
    enumii
    -0.79
     enfans
    -0.73
    enumi
    -0.73
     auroit
    -0.72
     Reſ
    -0.71
     investissements
    -0.69
     végétale
    -0.69
     photolibrary
    -0.68
    ')['
    -0.68
    POSITIVE LOGITS
     can
    0.79
     will
    0.58
     leads
    0.51
    hasMoreElements
    0.50
     is
    0.50
     it
    0.49
    ,
    0.49
    Przypisy
    0.48
     alters
    0.47
     defaultstate
    0.47
    Activations Density 8.233%

    No Known Activations