© 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. 6755
    Prev
    Next
    INDEX
    Explanations

    words related to business transactions, followed by conjunctions and words ending in "that"

    oai_token-act-pair · gemini-2.0-flash

    technical research texts

    np_max-act-logits · gemini-2.0-flash
    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
     We
    -1.88
     us
    -1.66
    We
    -1.45
     Мы
    -1.29
     Our
    -1.03
    Wir
    -1.01
     Nous
    -0.98
     Chúng
    -0.97
     WE
    -0.96
     Wir
    -0.94
    POSITIVE LOGITS
    PyTuple
    0.59
     Him
    0.58
    RectangleBorder
    0.57
     HIM
    0.57
    StructEnd
    0.54
    (&:
    0.54
     OnTriggerEnter
    0.53
     bych
    0.53
     Мексичка
    0.52
     me
    0.52
    Activations Density 3.687%

    No Known Activations