© 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. 5617
    Prev
    Next
    INDEX
    Explanations

    instances of the word "amp" either on its own or as part of a longer word

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "Amp"

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

    amp

    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
     ragione
    -0.50
    rítica
    -0.47
    narod
    -0.44
     flechas
    -0.42
    estrogen
    -0.42
     sürü
    -0.42
    등학교
    -0.42
     ocurre
    -0.40
     stating
    -0.40
    amarca
    -0.40
    POSITIVE LOGITS
    Diwedd
    0.90
     propOrder
    0.85
     चीज़ों
    0.85
    parsedMessage
    0.81
     مشين
    0.77
     Signalez
    0.73
    DockStyle
    0.72
    aarrggbb
    0.72
     unknownFields
    0.69
    下载附件
    0.69
    Activations Density 0.396%

    No Known Activations