© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14202
    Prev
    Next
    INDEX
    Explanations

    uses of the words "is", "are", and "was", plus some other words that often appear with them

    oai_token-act-pair · 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
     دیکھیے
    -0.65
     ujednoznacz
    -0.62
     TextAppearance
    -0.57
     ModelExpression
    -0.56
    +#+#
    -0.55
    PreferredItem
    -0.55
    CLC
    -0.54
     esposo
    -0.53
    encodeWith
    -0.53
    tvguidetime
    -0.52
    POSITIVE LOGITS
     Wales
    0.62
    Specialist
    0.60
     Specialist
    0.59
    trous
    0.58
     down
    0.58
    specialist
    0.57
    Nearest
    0.57
    Wales
    0.56
    ednesdays
    0.55
     Kamil
    0.55
    Activations Density 1.199%

    No Known Activations