© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14724
    Prev
    Next
    INDEX
    Explanations

    language-related words in a discussion about language

    oai_token-act-pair · gemini-2.0-flash

    speak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    __':
    -0.65
    /**
    -0.60
     FetchType
    -0.60
     CascadeType
    -0.55
    OGND
    -0.55
    astify
    -0.55
    rungsseite
    -0.54
     }}"></
    -0.54
    Xna
    -0.52
    DeleteBehavior
    -0.50
    POSITIVE LOGITS
     speak
    2.61
     speaks
    2.34
     speaking
    2.31
     Speak
    2.16
    speak
    2.09
    speaking
    2.02
     language
    1.99
    Speak
    1.97
     Speaking
    1.91
     spoke
    1.91
    Activations Density 3.143%

    No Known Activations