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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 842
    Prev
    Next
    INDEX
    Explanations

    words related to the attributes of immersive, expansive video games

    oai_token-act-pair · gemini-2.0-flash

    Video game reviews/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UrlResolution
    -0.63
     لينك
    -0.55
    ConstraintMaker
    -0.50
    UnsafeEnabled
    -0.50
    ]]
    -0.49
    ͍
    -0.47
    ytale
    -0.46
    rdom
    -0.46
     autorytatywna
    -0.45
     LTC
    -0.44
    POSITIVE LOGITS
     ویکی‌پدیای
    0.68
    ArgumentParser
    0.61
     CreateTagHelper
    0.61
     disambiguazione
    0.60
    Marshaller
    0.57
     EVIDENCE
    0.56
     evidences
    0.56
    קישורים
    0.53
     ujednoznacz
    0.53
    UNSIGNED
    0.51
    Activations Density 2.249%

    No Known Activations