© 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. 11862
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and certain auxiliary verbs that often accompany them.

    oai_token-act-pair · gemini-2.0-flash

    context-related phrases

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

    when

    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
     Eſ
    -0.65
     ſeveral
    -0.65
     Diſ
    -0.64
     greateſt
    -0.58
     ſtre
    -0.56
     Majefty
    -0.56
    testens
    -0.56
     Conſ
    -0.56
     Reſ
    -0.56
     ſy
    -0.55
    POSITIVE LOGITS
    ]")]
    0.93
     we
    0.88
     you
    0.66
    EndContext
    0.65
    oneofs
    0.60
     she
    0.59
     chi̍t
    0.58
     mình
    0.57
     shes
    0.57
    bootstrapcdn
    0.57
    Activations Density 0.671%

    No Known Activations