© 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. 6328
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with vehicles or driving

    oai_token-act-pair · gemini-2.0-flash

    terms related to adjustments or corrections

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

    adjustments

    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
    heça
    -0.56
    sizeCache
    -0.48
    zések
    -0.47
    ptid
    -0.46
     nổi
    -0.45
    ideae
    -0.43
     Söz
    -0.42
    throwaway
    -0.42
    startswith
    -0.41
     parlant
    -0.41
    POSITIVE LOGITS
     corrections
    0.78
    évaluateur
    0.78
     autorytatywna
    0.72
     correction
    0.69
     adjustments
    0.69
     adjustment
    0.68
     adap
    0.66
    adjust
    0.66
     يتيمه
    0.66
     adjusting
    0.64
    Activations Density 6.216%

    No Known Activations