© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6711
    Prev
    Next
    INDEX
    Explanations

    hypertext links "here" or phrases with "click here"

    oai_token-act-pair · gemini-2.0-flash

    here

    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
    BagConstraints
    -0.69
     EconPapers
    -0.69
     ་་
    -0.66
     myſelf
    -0.65
     Majefty
    -0.65
     Reſ
    -0.64
    featureID
    -0.64
     Midas
    -0.62
     ſta
    -0.60
    جوايز
    -0.60
    POSITIVE LOGITS
    endpush
    0.54
    :///
    0.44
    bigr
    0.44
    :
    0.42
     apparten
    0.39
     perpé
    0.39
    SaveChangesAsync
    0.38
    ContentAsync
    0.38
     quien
    0.38
    ReusableCell
    0.38
    Activations Density 0.405%

    No Known Activations