© 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. 13257
    Prev
    Next
    INDEX
    Explanations

    a wide range of sentence-starting words and interjections like "Oh", "So", "Lo", "There"

    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
     itſelf
    -1.23
     purpoſe
    -1.13
     Reſ
    -1.10
     myſelf
    -1.06
     Diſ
    -1.06
     pleaſure
    -1.05
    ſelf
    -1.05
     Eſ
    -1.02
     Houſe
    -1.01
     faſt
    -1.00
    POSITIVE LOGITS
    ,
    1.03
     no
    0.72
     Chwiliwch
    0.66
     I
    0.60
    UrlResolution
    0.60
     da
    0.57
    RegressionTest
    0.57
     lenker
    0.56
     ve
    0.54
    Abitanti
    0.54
    Activations Density 2.483%

    No Known Activations