© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4119
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese text related to sports

    oai_token-act-pair · gemini-2.0-flash

    Clothing items

    np_max-act-logits · gemini-2.0-flash

    clothing items

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    :✨
    -0.82
    RectangleBorder
    -0.71
    évaluateur
    -0.68
    principalColumn
    -0.66
    Personensuche
    -0.65
    发表于
    -0.65
    AddTagHelper
    -0.64
    BagLayout
    -0.64
     насељу
    -0.63
    complexContent
    -0.62
    POSITIVE LOGITS
     bolsillos
    0.68
    marginHorizontal
    0.66
     calcetines
    0.65
     chaleco
    0.63
     tacón
    0.61
     gorro
    0.61
     enfans
    0.59
     suéter
    0.57
     cepillo
    0.57
     cejas
    0.57
    Activations Density 0.429%

    No Known Activations