© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14696
    Prev
    Next
    INDEX
    Explanations

    words related to events and order

    oai_token-act-pair · gemini-2.0-flash

    say "as" words

    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
     as
    -2.89
    as
    -1.41
     sebagai
    -1.34
    作为
    -1.26
     как
    -1.26
     As
    -1.23
     ως
    -1.17
     као
    -1.13
    As
    -1.09
     як
    -1.09
    POSITIVE LOGITS
    has
    0.56
    OrBuilder
    0.51
    بوابة
    0.48
     has
    0.47
    +#+
    0.47
    HAS
    0.46
    रिक
    0.43
     HAS
    0.42
    الإنجليزية
    0.42
    TestingModule
    0.42
    Activations Density 0.923%

    No Known Activations