© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11448
    Prev
    Next
    INDEX
    Explanations

    instances of personal opinions or reflections

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'just'

    np_token-act-pair-logits · gpt-4o-mini

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mybatisplus
    -0.69
    خول
    -0.63
    ngdoc
    -0.58
     forState
    -0.56
     enige
    -0.56
     >=",
    -0.55
     IBOutlet
    -0.55
    請繼續往下閱讀
    -0.53
    ähkö
    -0.51
    Diwedd
    -0.51
    POSITIVE LOGITS
     just
    3.95
    just
    3.58
    Just
    3.08
     Just
    3.05
     JUST
    2.75
     juste
    2.48
    JUST
    2.45
     juft
    1.95
     appena
    1.91
     juſt
    1.88
    Activations Density 3.412%

    No Known Activations