© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    conjunctions, relative pronouns, and related words.

    oai_token-act-pair · gemini-2.0-flash

    references to narratives and storytelling

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

    them

    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
     their
    -2.44
    Their
    -2.38
     Their
    -2.25
    their
    -2.20
     THEIR
    -1.73
     leurs
    -1.58
     leur
    -1.48
     ihre
    -1.48
     deres
    -1.41
    他们的
    -1.38
    POSITIVE LOGITS
     them
    1.22
     itſelf
    0.88
    UserScript
    0.86
    them
    0.85
    AddHtmlAttribute
    0.85
     تانيه
    0.78
    ándolos
    0.77
     المعيارى
    0.74
    MLLoader
    0.74
     JAXBElement
    0.71
    Activations Density 1.470%

    No Known Activations