© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8470
    Prev
    Next
    INDEX
    Explanations

    the phrase "come forward" and the words "alive" and "favor"

    oai_token-act-pair · gemini-2.0-flash

    Action/Being, legal/celebration contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <eos>
    -0.64
     his
    -0.58
     kife
    -0.52
    a
    -0.50
     He
    -0.49
     he
    -0.47
    c
    -0.47
    -
    -0.47
     choice
    -0.46
     pod
    -0.46
    POSITIVE LOGITS
     Roskov
    1.20
     يتيمه
    1.09
     فريبيس
    0.99
     kasarigan
    0.95
    CloseOperation
    0.94
    BeginContext
    0.94
     שוליים
    0.94
    AndEndTag
    0.91
    routeProvider
    0.91
     мәкал
    0.90
    Activations Density 0.128%

    No Known Activations