© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7991
    Prev
    Next
    INDEX
    Explanations

    a constellation of seemingly random words, possibly from different languages, related to some technical context

    oai_token-act-pair · gemini-2.0-flash

    Possibly foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    detectChanges
    -0.73
    /***/
    -0.66
    principalColumn
    -0.60
    slidesPer
    -0.59
     خارجية
    -0.59
    adaptiveStyles
    -0.58
    leuth
    -0.58
     كومونز
    -0.57
    PreferredItem
    -0.56
    ("")]
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.60
    urator
    0.52
     compartment
    0.50
    wyl
    0.48
     Clooney
    0.48
     compartments
    0.47
    öra
    0.47
    Elektron
    0.46
    améli
    0.45
     upra
    0.45
    Activations Density 11.961%

    No Known Activations