© 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. 5908
    Prev
    Next
    INDEX
    Explanations

    talk about church or religion referencing a person who made a speech or gave a sermon

    oai_token-act-pair · gemini-2.0-flash

    Delivery

    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
     hears
    -1.08
     hear
    -1.05
     hearing
    -1.04
     listen
    -1.03
     heard
    -0.97
     listened
    -0.96
     listening
    -0.96
     listens
    -0.95
     HEAR
    -0.94
     LISTEN
    -0.92
    POSITIVE LOGITS
     delivery
    0.66
     Delivery
    0.60
    delivery
    0.59
    Delivery
    0.57
     DELIVERY
    0.52
    ArgsConstructor
    0.51
     delivered
    0.47
    DELIVERY
    0.46
     доставка
    0.45
    มาะ
    0.45
    Activations Density 1.346%

    No Known Activations