© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are important to marketing and also words ending in "y"

    oai_token-act-pair · gemini-2.0-flash

    say "y"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RegressionTest
    -0.57
     autorytatywna
    -0.54
    ValueGenerated
    -0.49
    帖最后由
    -0.48
     vulgaires
    -0.46
    )_/¯
    -0.45
    ṃ
    -0.45
     Princip
    -0.44
    '])->
    -0.44
     disponibilités
    -0.44
    POSITIVE LOGITS
    y
    2.77
    Y
    1.19
    yto
    1.18
    yv
    1.16
    ymal
    1.13
    ie
    1.09
    yny
    1.04
    yth
    1.02
    yse
    1.01
    ydi
    1.00
    Activations Density 6.516%

    No Known Activations