© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 349
    Prev
    Next
    INDEX
    Explanations

    words ending in "al" or "ally", with slight activation on the word "the"

    oai_token-act-pair · gemini-2.0-flash

    Words ending in ical/cial/ative/formally/official

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    inaison
    -0.52
     vedo
    -0.50
    дели
    -0.46
    mead
    -0.45
    entyfik
    -0.44
    esserung
    -0.43
     représ
    -0.42
    ControllerAdvice
    -0.42
    XmlAccessorType
    -0.42
    Neste
    -0.41
    POSITIVE LOGITS
    Offic
    0.85
    official
    0.84
    OFFICIAL
    0.84
     Officially
    0.82
    offic
    0.82
     رسمی
    0.80
    oficial
    0.80
     officially
    0.79
     officiel
    0.78
     offiziell
    0.77
    Activations Density 1.063%

    No Known Activations