© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11287
    Prev
    Next
    INDEX
    Explanations

    academic references, especially URLs and DOIs

    oai_token-act-pair · gemini-2.0-flash

    doi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.81
    '];?>
    -0.42
     p
    -0.39
    ↵↵
    -0.39
     u
    -0.39
    CommandType
    -0.38
     G
    -0.38
    cedido
    -0.36
    '])){
    -0.36
     muchas
    -0.35
    POSITIVE LOGITS
     Efq
    1.07
     ProtoMessage
    1.05
     Monfieur
    1.04
    kloped
    0.91
     Theſe
    0.88
    NameInMap
    0.87
     becauſe
    0.84
    matchCondition
    0.83
    Erreferentziak
    0.81
     ―――――
    0.81
    Activations Density 1.251%

    No Known Activations