© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2501
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "that" or the phrase "as if" and generally flags sentences with conditional or speculative language.

    oai_token-act-pair · gemini-2.0-flash

    hypothetical conditionals

    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
    Trama
    -0.53
    ymce
    -0.48
    getStringExtra
    -0.46
     Colla
    -0.45
     NUnit
    -0.45
     partiellement
    -0.45
    nyttet
    -0.45
    uttavia
    -0.45
    juana
    -0.44
    elstein
    -0.44
    POSITIVE LOGITS
    BagLayout
    0.68
    CloseOperation
    0.59
    Бахар
    0.58
    HideFlags
    0.58
     تكبرها
    0.56
    يميديا
    0.54
    ConverterFactory
    0.54
    DriverManager
    0.54
    DatabaseError
    0.53
    ="@+
    0.53
    Activations Density 0.656%

    No Known Activations