© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10434
    Prev
    Next
    INDEX
    Explanations

    the word "the" and the words "House" and "Office", as well as content about politics and the White House

    oai_token-act-pair · gemini-2.0-flash

    White

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -0.74
    хьтан
    -0.69
     defaultstate
    -0.68
     kaynağından
    -0.65
     >=",
    -0.59
    TypedDataSet
    -0.59
    principalTable
    -0.58
    NameInMap
    -0.58
    interopRequire
    -0.57
     ivelany
    -0.57
    POSITIVE LOGITS
     White
    1.73
    White
    1.59
     WHITE
    1.43
    WHITE
    1.39
     white
    1.32
    white
    1.25
    白
    1.14
     白
    1.04
    的白
    1.02
    ホワイト
    0.95
    Activations Density 1.737%

    No Known Activations