© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    phrases using "something", "anything" and "has to do with".

    oai_token-act-pair · gemini-2.0-flash

    relate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    зулта
    -0.54
    はじめに
    -0.54
    verwijspagina
    -0.54
     مرئيه
    -0.48
    änä
    -0.46
    setTo
    -0.45
    NAN
    -0.44
     volgt
    -0.42
     folgte
    -0.41
    yfikacja
    -0.41
    POSITIVE LOGITS
     related
    1.21
     relate
    1.13
     relates
    1.13
     relating
    1.04
    related
    1.03
     relacionado
    0.96
    relate
    0.95
     Related
    0.90
     berkaitan
    0.88
     relacion
    0.88
    Activations Density 2.224%

    No Known Activations