© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    positive adjectives or opportunities

    oai_token-act-pair · gemini-2.0-flash

    offer

    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
    ləş
    -0.39
    кса
    -0.39
     legen
    -0.39
     Wain
    -0.39
    вная
    -0.39
     heavily
    -0.38
    навли
    -0.38
    छे
    -0.38
     biểu
    -0.38
     chi̍t
    -0.38
    POSITIVE LOGITS
     offered
    1.47
     OFFER
    1.36
     offer
    1.35
    offered
    1.34
     available
    1.27
     Offered
    1.25
    Offered
    1.23
     afforded
    1.20
     provided
    1.20
     Offer
    1.20
    Activations Density 3.248%

    No Known Activations