© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" near the word "to".

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    featureID
    -0.64
     kaarangay
    -0.63
    basicConfig
    -0.63
    ViewFeatures
    -0.62
    ьаж
    -0.62
     utafitiHapana
    -0.60
    GEBURTSDATUM
    -0.59
    NameInMap
    -0.59
    TestingModule
    -0.58
    BrowserModule
    -0.57
    POSITIVE LOGITS
     bross
    0.56
    IActionResult
    0.53
     silang
    0.53
    ulihan
    0.52
     článku
    0.51
     vectorielles
    0.51
    ͘
    0.49
    sendStatus
    0.48
    mandu
    0.48
    ENTE
    0.47
    Activations Density 1.012%

    No Known Activations