© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14576
    Prev
    Next
    INDEX
    Explanations

    words associated with communication or arguments

    oai_token-act-pair · gemini-2.0-flash

    speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     >=",
    -0.70
     myſelf
    -0.58
    osomes
    -0.57
    στε
    -0.56
    ActionCreators
    -0.56
     implic
    -0.54
    cotta
    -0.54
     pain
    -0.54
    ","");
    -0.53
     rejo
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.75
     OFDb
    0.61
     møte
    0.54
     JADX
    0.52
     estekak
    0.52
     entendu
    0.52
    ContentAsync
    0.51
    MigrationBuilder
    0.51
    IsContent
    0.50
     humaine
    0.50
    Activations Density 2.580%

    No Known Activations