© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9746
    Prev
    Next
    INDEX
    Explanations

    phrases about feeling at home or finding a place to live

    oai_token-act-pair · gemini-2.0-flash

    home

    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
    ">//
    -0.65
     Paglinawan
    -0.62
     actionMode
    -0.60
    ⓧ
    -0.58
     createSlice
    -0.57
    MLLoader
    -0.57
    CodeAnalysis
    -0.57
    цезда
    -0.56
    WireFormatLite
    -0.55
    oredCriteria
    -0.55
    POSITIVE LOGITS
     home
    2.80
    home
    2.33
     HOME
    2.09
     Home
    2.08
    Home
    2.08
    HOME
    1.89
     homes
    1.60
     hjem
    1.59
     thuis
    1.58
     hogar
    1.56
    Activations Density 1.764%

    No Known Activations