© 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. 9467
    Prev
    Next
    INDEX
    Explanations

    the word "word," plus related items like "letters" and "voice."

    oai_token-act-pair · gemini-2.0-flash

    word/words

    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
     متعلقه
    -0.68
    enumii
    -0.67
    
    -0.66
    /**
    -0.66
    expandindo
    -0.64
    Zeneca
    -0.64
    RUnlock
    -0.64
    
    -0.63
    Diweddarwch
    -0.63
    utilisons
    -0.62
    POSITIVE LOGITS
     fit
    0.49
    fit
    0.46
    RegistryLite
    0.44
    TagHelpers
    0.43
    Reb
    0.42
    goog
    0.42
     less
    0.40
    LEncoder
    0.39
    msgSender
    0.39
    GenerationType
    0.39
    Activations Density 8.805%

    No Known Activations