© 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. 3991
    Prev
    Next
    INDEX
    Explanations

    words occurring right after or before prepositions such as "of", "to", "or", "in", etc

    oai_token-act-pair · gemini-2.0-flash

    Scraped/incomplete text

    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
     EconPapers
    -0.61
    PutMapping
    -0.48
    sizeCache
    -0.45
    nodoc
    -0.45
     CreateTagHelper
    -0.44
    ValueStyle
    -0.42
     pinulongan
    -0.42
    ³)
    -0.41
    excellents
    -0.41
     trúc
    -0.40
    POSITIVE LOGITS
    +#+
    0.63
    abetes
    0.61
     дописавши
    0.60
    ::_('
    0.59
    CPtr
    0.56
    LLocation
    0.55
    findpost
    0.55
    sightly
    0.55
    MeV
    0.52
    gameserver
    0.51
    Activations Density 0.507%

    No Known Activations