Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1170
    Prev
    Next
    INDEX
    Explanations

    references to legal and financial documents or proceedings, including citations, dates, and numbers

    oai_token-act-pair · gemini-2.0-flash

    legal/financial documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    Personendaten
    -0.69
    Personensuche
    -0.66
    انيف
    -0.65
     незавершена
    -0.64
    RuleContext
    -0.60
    NameInMap
    -0.60
    versammlung
    -0.59
     noDo
    -0.58
    __*/
    -0.57
     مرئيه
    -0.56
    POSITIVE LOGITS
    Begriffsklä
    0.51
    stdafx
    0.47
    RefNanny
    0.47
    FirstResponder
    0.47
     Kap
    0.46
    Erreferentziak
    0.45
    SFER
    0.44
     amanecer
    0.44
     newData
    0.44
    NewReader
    0.44
    Activations Density 4.445%

    No Known Activations