© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6772
    Prev
    Next
    INDEX
    Explanations

    the words "to" and "and".

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or code elements

    np_token-act-pair-logits · gpt-4o-mini

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    UpInside
    -0.54
    AccessorTable
    -0.52
    artet
    -0.47
     سكانية
    -0.46
    XmlAccessType
    -0.46
    Vorlage
    -0.44
    openzeppelin
    -0.44
     Theſe
    -0.42
     theſe
    -0.41
    eavour
    -0.41
    POSITIVE LOGITS
     nakalista
    0.68
    findpost
    0.66
    StoreMessageInfo
    0.66
    
    0.63
    InitVars
    0.63
    UnknownFields
    0.60
     nahilalakip
    0.60
    }^{+\
    0.60
     Italijanski
    0.59
     surla
    0.59
    Activations Density 5.303%

    No Known Activations