© 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. 15864
    Prev
    Next
    INDEX
    Explanations

    words related to history, geography and social science

    oai_token-act-pair · 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
     continues
    -1.38
     remains
    -1.30
     continue
    -1.29
    continues
    -1.28
     Continues
    -1.19
    remains
    -1.14
    continue
    -1.13
     remain
    -1.08
     Continue
    -1.05
     Remains
    -1.05
    POSITIVE LOGITS
     lived
    0.53
    urfs
    0.50
     stuck
    0.50
    RUnlock
    0.50
     kept
    0.48
    parseLong
    0.48
    throated
    0.48
    IPMENT
    0.47
    はじめに
    0.47
    țiunea
    0.46
    Activations Density 1.728%

    No Known Activations