© 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. 7606
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases that quantify a concept like 'day-to-day', possibly also finding references or numerical labeling

    oai_token-act-pair · gemini-2.0-flash

    -

    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
     ujednoznacz
    -0.64
     fleste
    -0.59
     prossima
    -0.57
     monumentos
    -0.53
     maggior
    -0.52
     nationaux
    -0.51
     prochain
    -0.51
     présidenti
    -0.50
     démocr
    -0.50
     durata
    -0.50
    POSITIVE LOGITS
    in
    0.94
    at
    0.90
    of
    0.77
    webElementGuid
    0.69
    ViewImports
    0.67
    GenerationType
    0.65
    PRWEB
    0.62
     ExecuteAsync
    0.62
    are
    0.60
    IN
    0.59
    Activations Density 15.742%

    No Known Activations