© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9548
    Prev
    Next
    INDEX
    Explanations

    phrases describing aiming products at a broad audience for business purposes

    oai_token-act-pair · gemini-2.0-flash

    markets and audience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    hoeddwyd
    -0.52
    RegressionTest
    -0.49
     razie
    -0.45
    tablissement
    -0.43
    šť
    -0.42
    trina
    -0.40
    tements
    -0.40
    WriteTagHelper
    -0.39
    рее
    -0.39
     Weing
    -0.38
    POSITIVE LOGITS
     markets
    1.91
     market
    1.91
    markets
    1.65
     Markets
    1.64
    market
    1.63
     audience
    1.62
     Market
    1.59
    Market
    1.55
    Markets
    1.48
     audiences
    1.48
    Activations Density 1.872%

    No Known Activations