© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6735
    Prev
    Next
    INDEX
    Explanations

    phrases related to underlying scientific mechanisms and processes, particularly in the context of medical research and injury.

    oai_token-act-pair · gemini-2.0-flash

    underlying mechanisms

    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
     MECHAN
    -2.09
     Mechanism
    -2.03
    mechan
    -2.00
     mechanism
    -1.97
    mechanism
    -1.92
    Mechanism
    -1.92
     Mechan
    -1.91
     mechanisms
    -1.84
    MECHAN
    -1.83
    Mechan
    -1.82
    POSITIVE LOGITS
    writeField
    0.78
    BeginContext
    0.71
    <?
    0.68
     تضيفلها
    0.65
    rungsseite
    0.64
     me
    0.63
    PreferredItem
    0.63
    ViewFeatures
    0.60
     vPvB
    0.59
    клопе
    0.59
    Activations Density 3.508%

    No Known Activations