© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5127
    Prev
    Next
    INDEX
    Explanations

    mentions of "institute of" followed by certain other mostly single words

    oai_token-act-pair · gemini-2.0-flash

    specific institutional names or identifiers

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

    of, for

    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
    nesi
    -0.45
    🏻
    -0.44
    kerne
    -0.43
    ESSION
    -0.40
     c
    -0.37
    wein
    -0.36
    .
    -0.35
    叮
    -0.35
     href
    -0.35
    🏼
    -0.35
    POSITIVE LOGITS
     utafitiHapana
    1.00
     للاسماء
    0.95
    Билгалдахарш
    0.88
    SequentialGroup
    0.85
    IndentedString
    0.83
     ModelExpression
    0.82
    tanleria
    0.82
    ंदीखरीदारी
    0.81
    awtextra
    0.81
    SharedDtor
    0.80
    Activations Density 0.663%

    No Known Activations