© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    passages in the first person recounting activities and anecdotes, or discussing personal states such as sleeping and eating.

    oai_token-act-pair · gemini-2.0-flash

    fall

    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
     beginnetje
    -0.62
    XmlAccessorType
    -0.55
    AddTagHelper
    -0.54
    bewerken
    -0.54
    GEBURTSDATUM
    -0.52
    ITIC
    -0.51
    انجليز
    -0.51
    雍
    -0.51
    awaiter
    -0.51
     Stimm
    -0.51
    POSITIVE LOGITS
     falling
    1.51
     falls
    1.45
     fell
    1.44
     fall
    1.41
     fallen
    1.30
     Falling
    1.26
    falling
    1.25
    fall
    1.20
     Fall
    1.18
    Fall
    1.16
    Activations Density 2.472%

    No Known Activations