© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3564
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to calls to action and article continuation

    oai_token-act-pair · gemini-2.0-flash

    say "Reading"

    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
     read
    -1.30
     Click
    -1.25
     click
    -1.25
     Read
    -1.23
     Learn
    -1.14
     CLICK
    -1.14
    click
    -1.12
    read
    -1.08
     learn
    -1.07
    Learn
    -1.07
    POSITIVE LOGITS
    AtIndexPath
    0.43
    ernalia
    0.40
    ars
    0.40
    gação
    0.40
    enn
    0.39
    entum
    0.39
     in
    0.39
     at
    0.39
    era
    0.38
    ound
    0.38
    Activations Density 2.633%

    No Known Activations