© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4610
    Prev
    Next
    INDEX
    Explanations

    words that include the characters "ing", especially the words "coming" and "going" and the presence of the word "The"

    oai_token-act-pair · gemini-2.0-flash

    coming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -0.77
    -
    -0.73
    ↵↵
    -0.69
     for
    -0.69
    y
    -0.67
    !
    -0.66
    :
    -0.65
     
    -0.62
    o
    -0.62
     (
    -0.59
    POSITIVE LOGITS
    ſelves
    0.98
     ويكيپيديا
    0.94
    =\""
    0.93
     photolibrary
    0.91
    __;
    0.91
    biamo
    0.87
     незавершена
    0.85
    tanleria
    0.84
     Houſe
    0.84
     """
    0.83
    Activations Density 1.737%

    No Known Activations