© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9559
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     vPvB
    -0.60
     surla
    -0.59
     utafitiHapana
    -0.58
     Wikimedijinoj
    -0.55
    ConverterFactory
    -0.51
     endIndex
    -0.49
     censiti
    -0.49
     setCurrent
    -0.48
    Demografía
    -0.48
     bulky
    -0.48
    POSITIVE LOGITS
    hoven
    0.65
    ọa
    0.59
     dotenv
    0.57
     InputDecoration
    0.56
    epik
    0.56
    ridged
    0.55
    ORUM
    0.55
    athread
    0.54
    AnchorTagHelper
    0.54
     Colle
    0.54
    Activations Density 1.543%

    No Known Activations