© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    future tense verbs, especially those expressing intent to discuss, consider or summarize something.

    oai_token-act-pair · gemini-2.0-flash

    Beginning of writing

    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
    __(/*!
    -0.82
     OFDb
    -0.80
     Exacts
    -0.73
     propOrder
    -0.73
    ValueStyle
    -0.73
     autorytatywna
    -0.72
     whoſe
    -0.72
    IndentedString
    -0.71
    GEBURTSDATUM
    -0.70
     ſtand
    -0.69
    POSITIVE LOGITS
    0.47
     tried
    0.46
    Nationalité
    0.45
     &
    0.43
     attempt
    0.43
     Home
    0.42
     attempts
    0.42
    BorderFactory
    0.41
     attempted
    0.40
     try
    0.39
    Activations Density 2.689%

    No Known Activations