© 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. 6137
    Prev
    Next
    INDEX
    Explanations

    articles about travel and radio

    oai_token-act-pair · gemini-2.0-flash

    the word 'every'

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

    say "every"

    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
    <bos>
    -0.47
     d
    -0.39
    tedy
    -0.38
    Ato
    -0.38
    ller
    -0.38
     i
    -0.38
     niya
    -0.37
    Etimo
    -0.36
    setz
    -0.36
    новништво
    -0.36
    POSITIVE LOGITS
     every
    2.41
    every
    2.16
    Every
    1.80
     Every
    1.77
     EVERY
    1.58
     ogni
    1.52
     setiap
    1.52
     Ogni
    1.40
    EVERY
    1.38
     κάθε
    1.37
    Activations Density 2.491%

    No Known Activations