© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7064
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "There"

    oai_token-act-pair · gemini-2.0-flash

    There

    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
    PreferredItem
    -0.90
    __':
    -0.83
    __":
    -0.75
    ")));
    -0.69
     متعلقه
    -0.68
     Biôgrafia
    -0.68
    таратура
    -0.66
    ptonshire
    -0.65
     Италијани
    -0.64
    ')));
    -0.63
    POSITIVE LOGITS
     there
    0.54
     nothing
    0.54
    Nothing
    0.49
     There
    0.48
     something
    0.47
    There
    0.47
     Nothing
    0.47
    NOTHING
    0.46
    EndContext
    0.46
     Something
    0.45
    Activations Density 0.201%

    No Known Activations