© 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. 9768
    Prev
    Next
    INDEX
    Explanations

    pronouns and related words like 'can', 'will', 'are'

    oai_token-act-pair · gemini-2.0-flash

    context of personal relationships and support

    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
    OGND
    -0.58
    LLocation
    -0.52
     sólidos
    -0.49
     gouvernements
    -0.48
    Datuak
    -0.48
     prisonniers
    -0.47
     logiciels
    -0.47
     engraçadas
    -0.47
     ujednoznacz
    -0.47
     citoy
    -0.46
    POSITIVE LOGITS
    jsii
    0.65
    ]!=
    0.64
     took
    0.56
     learned
    0.54
     kaynağından
    0.54
     bought
    0.54
    nologie
    0.53
    espère
    0.51
     can
    0.50
     mList
    0.50
    Activations Density 1.270%

    No Known Activations