© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16240
    Prev
    Next
    INDEX
    Explanations

    the word "type" and other words in JSON schemas and also finds "name", "price" and "cash back"

    oai_token-act-pair · gemini-2.0-flash

    publishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ”:
    -1.16
    “:
    -1.09
    :”
    -1.09
    ’:
    -1.06
    "):
    -1.04
    ”).
    -1.02
    ?):
    -0.99
    ”),
    -0.96
    '):
    -0.96
    ),”
    -0.95
    POSITIVE LOGITS
    Publication
    0.87
     publishers
    0.84
     publishing
    0.78
     publish
    0.77
    Publish
    0.77
     publication
    0.77
     Publish
    0.73
     publisher
    0.73
     publications
    0.73
    PUBLISH
    0.73
    Activations Density 0.738%

    No Known Activations