© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14028
    Prev
    Next
    INDEX
    Explanations

    the word "of" or the phrase "similar to"

    oai_token-act-pair · gemini-2.0-flash

    ownership and relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     your
    -1.63
     my
    -1.44
    your
    -1.20
     our
    -1.20
     their
    -1.09
     her
    -1.05
    my
    -1.05
     thy
    -1.02
    你的
    -0.98
     seu
    -0.96
    POSITIVE LOGITS
    omeness
    0.61
    Él
    0.60
     initComponents
    0.56
    IndentedString
    0.55
     esternos
    0.54
    Sucesor
    0.51
     Meksiku
    0.50
    MetaObject
    0.49
     EconPapers
    0.47
    gbaar
    0.47
    Activations Density 0.374%

    No Known Activations