© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    fragments of the word "deciding"

    oai_token-act-pair · gemini-2.0-flash

    Dec

    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
     isNameExpr
    -0.48
     protoimpl
    -0.48
    ölker
    -0.47
    Autoritní
    -0.46
     Roskov
    -0.45
     vasca
    -0.45
     ninh
    -0.45
     län
    -0.44
     coldly
    -0.44
    جمعیت
    -0.44
    POSITIVE LOGITS
     تانيه
    0.66
    ]";
    0.61
    )}</
    0.61
     Majefty
    0.59
    parsedMessage
    0.57
    存于互联网档案馆
    0.56
     XNUMX
    0.56
    ,‎
    0.56
    )"),
    0.56
     <=",
    0.55
    Activations Density 0.487%

    No Known Activations