© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14696
    Prev
    Next
    INDEX
    Explanations

    language related to geological surveys for oil and gas

    oai_token-act-pair · gemini-2.0-flash

    Geological surveys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     EconPapers
    -0.63
     дописавши
    -0.55
     חיצוניים
    -0.54
    nodoc
    -0.48
    Класс
    -0.45
    enumii
    -0.45
    يميديا
    -0.44
    <![
    -0.43
    nthetic
    -0.42
     ويكيپيديا
    -0.42
    POSITIVE LOGITS
    OGND
    0.58
    Життєпис
    0.56
    SerializedSize
    0.55
    Története
    0.55
    addCriterion
    0.54
    mybatisplus
    0.54
    InstrumentedTest
    0.54
    newArrayList
    0.53
    errHandler
    0.52
    Przypisy
    0.50
    Activations Density 4.926%

    No Known Activations