© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11344
    Prev
    Next
    INDEX
    Explanations

    the word "Bas" at the start of a word

    oai_token-act-pair · gemini-2.0-flash

    concepts related to bases

    np_token-act-pair-logits · gpt-4o-mini

    Pasifika or Basilian

    np_max-act-logits · gemini-2.0-flash

    bas

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    fractive
    -0.49
    tslib
    -0.47
    tonsoft
    -0.45
    стюм
    -0.45
    pañol
    -0.43
     pic
    -0.42
    وضوع
    -0.41
    rest
    -0.41
     addressed
    -0.40
     rest
    -0.40
    POSITIVE LOGITS
    SequentialGroup
    0.81
    ⓧ
    0.72
    hyrchwyd
    0.65
     >=",
    0.65
     AssemblyProduct
    0.65
    ftagPool
    0.64
    GEBURTSDATUM
    0.64
     للمعارف
    0.63
     otomatig
    0.63
    stylers
    0.60
    Activations Density 0.404%

    No Known Activations