© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7460
    Prev
    Next
    INDEX
    Explanations

    a variety of short, common words like articles, prepositions, pronouns, and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    variations of "get"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     obtained
    -0.77
    obtained
    -0.76
     myſelf
    -0.71
     faſt
    -0.69
     Jefus
    -0.68
     Obtained
    -0.68
     obtaining
    -0.66
    :✨
    -0.66
     ſame
    -0.65
     poffe
    -0.65
    POSITIVE LOGITS
     get
    2.02
     Get
    1.73
     gets
    1.63
    get
    1.61
     getting
    1.59
    Get
    1.55
     GET
    1.45
     Getting
    1.41
     gotten
    1.38
     Gets
    1.35
    Activations Density 3.825%

    No Known Activations