© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    words related to organized events, races, or competitions, especially those of a challenging nature

    oai_token-act-pair · gemini-2.0-flash

    running events

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.59
    assertRaises
    -0.59
    GOTREF
    -0.57
    ScopeManager
    -0.57
    delwed
    -0.55
    stringstream
    -0.55
    VersionUID
    -0.54
    RenderAtEndOf
    -0.54
     الحره
    -0.54
    GIVEREF
    -0.54
    POSITIVE LOGITS
    Rujuakan
    0.51
    ereum
    0.45
    Jeografia
    0.44
    SOUNDBITE
    0.43
     helyzet
    0.43
     transfé
    0.42
     ℃
    0.42
    phora
    0.42
     шту
    0.42
     województwie
    0.41
    Activations Density 8.110%

    No Known Activations