© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13267
    Prev
    Next
    INDEX
    Explanations

    capitalized letter P at the beginning of a line or after white space

    oai_token-act-pair · gemini-2.0-flash

    P

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    h
    -0.52
    pit
    -0.51
    oci
    -0.48
    ose
    -0.48
    ضية
    -0.47
    od
    -0.47
    ogene
    -0.46
    pson
    -0.46
     fewer
    -0.45
    thâu
    -0.45
    POSITIVE LOGITS
    GeneratedCode
    0.65
     Wikimedijinoj
    0.62
    ILayout
    0.58
     abbraccio
    0.56
    DotNetBar
    0.54
     fallacy
    0.54
     Inquisition
    0.53
    MLLoader
    0.53
     оригіналу
    0.53
     RIPRODUZIONE
    0.52
    Activations Density 2.894%

    No Known Activations