© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1971
    Prev
    Next
    INDEX
    Explanations

    scientific and technical text related to materials or chemistry

    oai_token-act-pair · gemini-2.0-flash

    industry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     INTERESAR
    -0.64
     wikipagina
    -0.57
     indisponible
    -0.56
    Wpf
    -0.56
    UnitTesting
    -0.54
     ExecuteAsync
    -0.53
     asupra
    -0.53
     onward
    -0.52
    expandindo
    -0.52
     виправивши
    -0.51
    POSITIVE LOGITS
     كومونز
    0.65
    OGND
    0.60
    Geografi
    0.56
    letic
    0.55
     Италијани
    0.54
    цездатний
    0.49
    GIVEREF
    0.49
    Traducción
    0.49
    SequentialGroup
    0.49
    <bos>
    0.49
    Activations Density 47.341%

    No Known Activations