© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9156
    Prev
    Next
    INDEX
    Explanations

    the suffixes "eth" and "ety" which often appear in numbers and ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    Legal documents and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     "
    -0.54
    abadi
    -0.50
    tetlen
    -0.46
     '
    -0.45
    Pvt
    -0.43
    ánh
    -0.42
    orean
    -0.40
    rance
    -0.40
     gra
    -0.38
    тесь
    -0.38
    POSITIVE LOGITS
     Vikipedi
    1.04
     Sixteen
    0.94
    Eight
    0.94
     Sixty
    0.93
     sixteen
    0.93
     eighty
    0.93
     Eight
    0.93
     eight
    0.92
     Eighteen
    0.89
    six
    0.88
    Activations Density 0.335%

    No Known Activations