© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    references to traumatic or emotional experiences.

    oai_token-act-pair · gemini-2.0-flash

    sentence continuations

    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
     Italijani
    -0.70
     onCreateView
    -0.69
    GEBURTSDATUM
    -0.68
    HideFlags
    -0.62
    UnusedPrivate
    -0.60
    IBarButtonItem
    -0.59
    queryInterface
    -0.59
    UserScript
    -0.57
     geografic
    -0.57
    tonsoft
    -0.55
    POSITIVE LOGITS
     about
    0.71
     urmă
    0.58
     defaultstate
    0.57
     gambe
    0.56
     esigenze
    0.56
     őket
    0.55
     his
    0.55
     dieux
    0.54
    about
    0.53
     saumon
    0.53
    Activations Density 11.740%

    No Known Activations