© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13107
    Prev
    Next
    INDEX
    Explanations

    location names either in Australia or related to Australia

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     disambiguazione
    -0.60
    wikidata
    -0.59
     }),
    -0.51
     initWithFrame
    -0.51
     NKC
    -0.50
    مصادر
    -0.50
    ztes
    -0.49
    .)}
    -0.49
    chanical
    -0.48
    rahat
    -0.48
    POSITIVE LOGITS
    клопе
    0.58
    łgorzata
    0.54
    PSON
    0.54
     ſta
    0.51
    CAPITULO
    0.51
    ględ
    0.49
    TypedValue
    0.49
    basicConfig
    0.49
    Объ
    0.49
    MockBean
    0.49
    Activations Density 3.590%

    No Known Activations