© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9927
    Prev
    Next
    INDEX
    Explanations

    words related to gambling, casinos, slot machines, and related apps

    oai_token-act-pair · gemini-2.0-flash

    casino

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    +#+#
    -0.70
     >=",
    -0.68
     autorità
    -0.66
    Portail
    -0.66
     odeur
    -0.63
    NameInMap
    -0.61
    mybatisplus
    -0.60
     فريبيس
    -0.60
    ức
    -0.60
     المعيارى
    -0.60
    POSITIVE LOGITS
     mic
    0.45
    sterone
    0.42
     surla
    0.38
    Widths
    0.38
    achi
    0.37
    nodoc
    0.36
    bní
    0.36
     melt
    0.36
    Uninitialized
    0.36
    uzz
    0.36
    Activations Density 2.830%

    No Known Activations