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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9961
    Prev
    Next
    INDEX
    Explanations

    phrases which include the word "at"

    oai_token-act-pair · gemini-2.0-flash

    programming concepts or terms

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

    at

    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
    tothe
    -0.55
     Zel
    -0.49
    oup
    -0.48
    Applies
    -0.47
    oredCriteria
    -0.47
     toa
    -0.47
    ToDouble
    -0.45
    <bos>
    -0.45
     "..\..\
    -0.45
    ∬
    -0.45
    POSITIVE LOGITS
    neté
    0.63
    initializeApp
    0.59
    +#+#
    0.58
    ScopeManager
    0.57
    UNTIME
    0.52
    NameInMap
    0.52
     profondément
    0.50
    Controlled
    0.50
    StructEnd
    0.50
     spē
    0.50
    Activations Density 0.702%

    No Known Activations