© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    words with suffixes such as "ed", "ly", "tion", "ize", "ize", "al" and prefixes such as "con", "sub", "inter"

    oai_token-act-pair · gemini-2.0-flash

    say "-ed" endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     to
    -0.48
    ,
    -0.45
     holding
    -0.44
    žo
    -0.44
     
    -0.43
    breaking
    -0.42
     from
    -0.41
     as
    -0.41
    Breaking
    -0.40
     Kühlschrank
    -0.39
    POSITIVE LOGITS
     disambiguazione
    0.89
     Roskov
    0.81
    parsedMessage
    0.81
     raiſ
    0.79
    graphed
    0.77
    inted
    0.75
    ised
    0.75
     ModelExpression
    0.75
    UnusedPrivate
    0.75
     CURIAM
    0.74
    Activations Density 1.003%

    No Known Activations