© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5721
    Prev
    Next
    INDEX
    Explanations

    the word "as" possibly followed by another word

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with 'as'

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

    as

    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
     ModelExpression
    -0.89
     ujednoznacz
    -0.75
     дописавши
    -0.68
     MUCH
    -0.62
    IsMutable
    -0.61
    ableness
    -0.60
    openConnection
    -0.59
     enough
    -0.59
    Хьажоргаш
    -0.58
    Much
    -0.57
    POSITIVE LOGITS
     large
    0.53
     wide
    0.52
    ________________
    0.49
     big
    0.47
    рп
    0.46
    emark
    0.45
    hesus
    0.45
    وزيع
    0.44
     bright
    0.43
    ResumeLayout
    0.43
    Activations Density 0.928%

    No Known Activations