© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14377
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PC"

    oai_token-act-pair · gemini-2.0-flash

    PC

    np_max-act · gemini-2.0-flash

    PC

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    son
    -0.63
    práv
    -0.62
     querían
    -0.62
     hubieran
    -0.62
     abbiano
    -0.61
     saben
    -0.60
     hablan
    -0.60
    THE
    -0.60
     pudieran
    -0.59
    SON
    -0.59
    POSITIVE LOGITS
     resourceCulture
    1.28
    Архівовано
    1.07
    IUrlHelper
    1.02
    SequentialGroup
    0.93
     يتيمه
    0.91
    .*")]
    0.91
    WebVitals
    0.91
     препратки
    0.88
    帖最后由
    0.86
    Décès
    0.85
    Activations Density 1.111%

    No Known Activations