© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    the phrase "don't let that put you off"

    oai_token-act-pair · gemini-2.0-flash

    let

    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
    NOPQRST
    -0.57
    buttonShape
    -0.52
    󠁣
    -0.46
     AssemblyProduct
    -0.46
    attet
    -0.45
    ToTop
    -0.45
     Polyp
    -0.45
    EXTERN
    -0.44
    >(&
    -0.44
     headboard
    -0.44
    POSITIVE LOGITS
    GraphicsUnit
    0.65
    CodedInputStream
    0.62
     Wikimédia
    0.62
    zają
    0.61
    webElementXpaths
    0.60
    addCriterion
    0.60
     Roskov
    0.60
     /\.(
    0.57
     sometimes
    0.57
    MethodManager
    0.57
    Activations Density 0.726%

    No Known Activations