© 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. 387
    Prev
    Next
    INDEX
    Explanations

    the words "on", "onward", or "forward" when next to words indicating a location

    oai_token-act-pair · gemini-2.0-flash

    forward direction

    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
     procedente
    -0.87
    sources
    -0.86
    FROM
    -0.83
     therefrom
    -0.83
     sources
    -0.83
     FROM
    -0.80
     CreateTagHelper
    -0.75
     procedentes
    -0.75
    来自
    -0.75
     proveniente
    -0.73
    POSITIVE LOGITS
    VIRGO
    0.47
    atí
    0.46
    iterranée
    0.44
    bnf
    0.44
     Thumbnails
    0.43
    ubar
    0.43
     poveznice
    0.43
    berge
    0.43
    dikan
    0.43
    群
    0.43
    Activations Density 1.435%

    No Known Activations