© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4016
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Ap" (likely standing for April) and the prefix "ap".

    oai_token-act-pair · gemini-2.0-flash

    say "Ap"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مرئيه
    -1.11
    GEBURTSDATUM
    -1.03
     Monfieur
    -0.93
     Chwiliwch
    -0.90
    WindowConstants
    -0.86
     myſelf
    -0.85
     leaſt
    -0.84
     AppModule
    -0.81
    interopRequire
    -0.80
     auroit
    -0.80
    POSITIVE LOGITS
     B
    0.46
    uros
    0.44
     th
    0.42
     c
    0.41
    ↵
    0.41
     Her
    0.40
     Haus
    0.40
     no
    0.39
     No
    0.39
     ar
    0.39
    Activations Density 0.774%

    No Known Activations