© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10917
    Prev
    Next
    INDEX
    Explanations

    HTML code related to tags

    oai_token-act-pair · gemini-2.0-flash

    tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     tag
    -3.02
    tag
    -2.78
    Tag
    -2.67
     Tag
    -2.59
     tags
    -2.48
    tags
    -2.20
     Tags
    -2.13
    TAG
    -2.06
    Tags
    -2.05
     tagging
    -2.03
    POSITIVE LOGITS
     protoimpl
    0.71
     للمعارف
    0.62
     kaarangay
    0.58
    рации
    0.53
    Rhestr
    0.51
    iants
    0.51
    maketitle
    0.51
    Pozri
    0.50
     autorytatywna
    0.50
     CreateTagHelper
    0.50
    Activations Density 0.638%

    No Known Activations