© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4486
    Prev
    Next
    INDEX
    Explanations

    technical writing in an academic paper, likely in a scientific field such as physics or chemistry

    oai_token-act-pair · gemini-2.0-flash

    This

    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
     defaultstate
    -0.54
    <bos>
    -0.47
    tagHelperRunner
    -0.44
     pronti
    -0.44
     skulls
    -0.41
    SqlQuery
    -0.41
     indoss
    -0.40
    tagem
    -0.39
    RectangleBorder
    -0.39
    jedis
    -0.38
    POSITIVE LOGITS
    ^(@)
    0.68
    Hochspringen
    0.59
    DockStyle
    0.58
    Portail
    0.58
    Portály
    0.58
    assumption
    0.55
    PhysRevD
    0.55
    }}^{(
    0.55
    RegressionTest
    0.54
    angdong
    0.54
    Activations Density 1.553%

    No Known Activations