Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14536
    Prev
    Next
    INDEX
    Explanations

    news articles about organizations or governments making announcements or taking action

    oai_token-act-pair · gemini-2.0-flash

    News, reports, statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    sizeCache
    -0.48
    WriteLiteral
    -0.47
    はじめに
    -0.46
    rungsseite
    -0.46
    #
    -0.45
    TRIBUT
    -0.43
    &__
    -0.43
    
    -0.41
    onymous
    -0.41
     supra
    -0.39
    POSITIVE LOGITS
    StructEnd
    0.67
     ++)
    0.66
     GeoNames
    0.66
    Portale
    0.63
    ContextHolder
    0.62
    RTDA
    0.61
     categorically
    0.60
    nath
    0.59
    ₁,
    0.57
     Cymru
    0.56
    Activations Density 1.600%

    No Known Activations