© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11712
    Prev
    Next
    INDEX
    Explanations

    commas and short words (especially "and") surrounded by mid-range (non-zero) activation values.

    oai_token-act-pair · gemini-2.0-flash

    non-English conjunctions and symbols

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

    comma

    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
    ,
    -0.81
    ...,
    -0.51
    principalColumn
    -0.50
     ExecuteAsync
    -0.50
     utafitiHapana
    -0.47
    ,,,
    -0.47
    ,
    -0.47
    ,,
    -0.44
    …,
    -0.43
    (),
    -0.43
    POSITIVE LOGITS
     and
    1.59
    Personendaten
    0.87
    และ
    0.78
    帖最后由
    0.78
     \&
    0.75
     및
    0.75
    تقاوى
    0.74
    الحياه
    0.73
    Sklici
    0.72
    &&(
    0.71
    Activations Density 1.682%

    No Known Activations