© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13810
    Prev
    Next
    INDEX
    Explanations

    the syllables/word "yoindaver", and to a lesser extent "wy" and "kai."

    oai_token-act-pair · gemini-2.0-flash

    yo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    yo
    -0.64
    InThe
    -0.58
    <bos>
    -0.57
    nictví
    -0.55
    utkan
    -0.54
     Osorio
    -0.53
    hwa
    -0.53
    ppie
    -0.52
    ,’’
    -0.52
    yle
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.84
    DeleteBehavior
    0.79
     leaſt
    0.68
     avoient
    0.65
     étoient
    0.64
    adaptiveStyles
    0.63
    jsxFileName
    0.63
    IBOutlet
    0.60
     étoit
    0.58
     Majefty
    0.58
    Activations Density 0.528%

    No Known Activations