© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11180
    Prev
    Next
    INDEX
    Explanations

    words related to retaining or modifying something

    oai_token-act-pair · gemini-2.0-flash

    store

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     store
    -2.63
    store
    -2.45
     Store
    -2.42
    Store
    -2.41
     stores
    -2.27
     STORE
    -2.25
    STORE
    -2.16
     Stores
    -2.13
    stores
    -2.03
    Stores
    -2.00
    POSITIVE LOGITS
     nakalista
    0.56
     vidare
    0.53
     correctes
    0.47
     useRouter
    0.44
    complexContent
    0.44
     fuch
    0.44
    เดียว
    0.43
    ándote
    0.43
    EdgeInsets
    0.43
    ombras
    0.43
    Activations Density 5.886%

    No Known Activations