© 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. 6201
    Prev
    Next
    INDEX
    Explanations

    the letter "E" next to numbers and other capital letters

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the letter 'E'

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

    E

    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
     ivelany
    -0.56
    q
    -0.54
     emberek
    -0.53
    expandindo
    -0.52
    xp
    -0.52
    ll
    -0.52
    nth
    -0.52
    quations
    -0.51
    quip
    -0.51
     implication
    -0.51
    POSITIVE LOGITS
    RegressionTest
    0.60
    or
    0.57
    om
    0.50
    al
    0.50
     cherchés
    0.49
    $_['
    0.49
     ordina
    0.48
    gameserver
    0.48
    omys
    0.48
    ChromeDriver
    0.47
    Activations Density 0.922%

    No Known Activations