© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3227
    Prev
    Next
    INDEX
    Explanations

    various conjugations of the verb "to get"

    oai_token-act-pair · gemini-2.0-flash

    references to past experiences

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

    got

    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
     AssemblyTitle
    -0.68
     estekak
    -0.66
    jmniej
    -0.64
    niająca
    -0.63
    脚注の使い方
    -0.63
    határoz
    -0.59
    ніципалі
    -0.57
    ERGY
    -0.56
    РЭ
    -0.56
     RequestMethod
    -0.56
    POSITIVE LOGITS
    Predecesor
    0.50
     home
    0.47
     theirs
    0.47
     homo
    0.47
     hers
    0.45
    ########.
    0.43
    发表于
    0.43
     bar
    0.43
    ldorf
    0.41
     elliptic
    0.41
    Activations Density 0.539%

    No Known Activations