© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PR" in various contexts, which possibly stands for pride or protein

    oai_token-act-pair · gemini-2.0-flash

    PR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     صوتيه
    -0.75
    quid
    -0.60
    ➟
    -0.57
    MLLoader
    -0.56
     FontWeight
    -0.56
    ragona
    -0.54
    λασ
    -0.53
    liflower
    -0.52
    urtstag
    -0.52
     trans
    -0.52
    POSITIVE LOGITS
    -------
    0.56
     виправивши
    0.49
     demikian
    0.47
    AÇÃO
    0.47
     morrow
    0.46
     Normdatei
    0.46
     tongs
    0.44
     Devotion
    0.44
    assembly
    0.43
     épic
    0.43
    Activations Density 0.409%

    No Known Activations