© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    strings of capital letters in a variety of contexts including academic citations, software code, and acronyms/initialisms

    oai_token-act-pair · gemini-2.0-flash

    References in brackets

    np_max-act-logits · gemini-2.0-flash

    suffixes

    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
     vermelhas
    -0.48
     brancas
    -0.46
     réguli
    -0.46
     normaux
    -0.44
     automatiques
    -0.38
     amitié
    -0.38
     Efq
    -0.36
     becauſe
    -0.36
     sauvages
    -0.36
     figliu
    -0.36
    POSITIVE LOGITS
    TERY
    0.69
    IUM
    0.68
    YNC
    0.68
    CHED
    0.68
    UAL
    0.68
    RIER
    0.66
    RESS
    0.66
    ROGEN
    0.66
    RIES
    0.66
    ULS
    0.66
    Activations Density 33.288%

    No Known Activations