© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4012
    Prev
    Next
    INDEX
    Explanations

    the word "state" when referring to a location or condition

    oai_token-act-pair · gemini-2.0-flash

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kasarigan
    -0.60
    SCT
    -0.53
     Ause
    -0.51
    ReactDOM
    -0.45
    ension
    -0.45
    enumii
    -0.44
     sliders
    -0.44
    entious
    -0.43
     forskjellige
    -0.43
    趾
    -0.43
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.78
    expandindo
    0.73
    Hentet
    0.66
     فريبيس
    0.65
    ########.
    0.63
    saraba
    0.63
    IntoConstraints
    0.63
     quo
    0.61
     Quo
    0.57
    Obrázky
    0.55
    Activations Density 1.300%

    No Known Activations