© 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. 13955
    Prev
    Next
    INDEX
    Explanations

    first person pronouns in questions and discussions about current activities or states

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "to be" and "to have"

    np_token-act-pair-logits · gpt-4o-mini
    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
     يتيمه
    -0.84
    ⓧ
    -0.69
    Einzelnachweise
    -0.65
     snippetHide
    -0.63
    NamedQueries
    -0.61
    
    -0.61
    zzly
    -0.58
    bewerken
    -0.57
    ThroughAttribute
    -0.57
    enumi
    -0.56
    POSITIVE LOGITS
     been
    1.02
    been
    0.92
     has
    0.91
     geweest
    0.90
     Been
    0.87
    Been
    0.84
     have
    0.83
    Has
    0.82
     telah
    0.81
     Has
    0.79
    Activations Density 1.013%

    No Known Activations