© 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. 5587
    Prev
    Next
    INDEX
    Explanations

    Croatian words relating to confirming or verifying via SMS or email

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "to be" (past)

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

    Were

    np_max-act-logits · gemini-2.0-flash
    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
    nodoc
    -0.50
     Wikimedijinoj
    -0.50
     initComponents
    -0.50
     рассказыва
    -0.50
     disponibilités
    -0.49
     сдела
    -0.48
     المعيارى
    -0.48
     الدولى
    -0.48
    SharedDtor
    -0.47
    니다
    -0.47
    POSITIVE LOGITS
     were
    0.95
    Were
    0.66
    were
    0.63
     Were
    0.63
     weren
    0.61
     WERE
    0.61
    xically
    0.55
     pinulongan
    0.54
     मिले
    0.53
    вели
    0.52
    Activations Density 0.326%

    No Known Activations