© 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. 1649
    Prev
    Next
    INDEX
    Explanations

    a mix of formatting instructions, file types, and coding language snippets

    oai_token-act-pair · gemini-2.0-flash

    text formatting/coding

    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
    ⓧ
    -0.69
    AndEndTag
    -0.68
    ]")]
    -0.65
     onBind
    -0.65
    offsetof
    -0.62
    multirow
    -0.62
     unknownFields
    -0.62
    iecie
    -0.59
    RUnlock
    -0.56
     Stir
    -0.56
    POSITIVE LOGITS
     nadzieję
    0.47
    Personendaten
    0.47
    amını
    0.47
     litri
    0.47
     canst
    0.45
    sieht
    0.42
    Zdroje
    0.42
     esboço
    0.42
    retmen
    0.42
    theoremstyle
    0.41
    Activations Density 1.829%

    No Known Activations