© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12595
    Prev
    Next
    INDEX
    Explanations

    first person pronouns in the context of historical family stories

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     memory
    -0.64
    memory
    -0.59
    Memory
    -0.58
     ever
    -0.58
     Memor
    -0.56
    memor
    -0.54
     remembered
    -0.53
     Memory
    -0.53
     remembers
    -0.53
    Ever
    -0.52
    POSITIVE LOGITS
     AssemblyCulture
    0.71
    ValueStyle
    0.71
     Paglinawan
    0.57
    OCCURRED
    0.56
    ruptedException
    0.56
    ItemClick
    0.55
    InitVars
    0.54
    MessageTagHelper
    0.53
    ForValue
    0.53
    RUnlock
    0.53
    Activations Density 1.871%

    No Known Activations