© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6097
    Prev
    Next
    INDEX
    Explanations

    words related to past tense verbs or emotions, sometimes in conversation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     chi̍t
    -0.80
    messageInfo
    -0.69
    :✨
    -0.69
     Theſe
    -0.68
    ///</
    -0.67
     ErrInvalid
    -0.67
    MigrationBuilder
    -0.67
     "..\..\
    -0.65
    PreferredItem
    -0.65
    AddHtmlAttribute
    -0.65
    POSITIVE LOGITS
    TypedDataSet
    0.48
     PhpStorm
    0.47
     қара
    0.46
    mar
    0.46
     étudié
    0.45
    斯基
    0.44
    睛
    0.43
    ρους
    0.42
    AccessorTable
    0.41
     b
    0.40
    Activations Density 3.518%

    No Known Activations