© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7581
    Prev
    Next
    INDEX
    Explanations

    punctuation, formatting marks, and non-English characters.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     Real
    -0.54
     Law
    -0.53
     Pat
    -0.50
     Sub
    -0.48
     Ste
    -0.47
    يكب
    -0.46
     Far
    -0.46
     Sh
    -0.46
     Long
    -0.46
    itself
    -0.45
    POSITIVE LOGITS
     opium
    0.86
     disarmament
    0.84
     solstice
    0.80
     constitutions
    0.78
     atheism
    0.77
    BeginContext
    0.77
     atonement
    0.77
     vengeance
    0.76
    ########.
    0.76
     heresy
    0.75
    Activations Density 4.236%

    No Known Activations