© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13726
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'given' followed by other words with a low activation

    oai_token-act-pair · gemini-2.0-flash

    given

    np_max-act-logits · gemini-2.0-flash

    instances of the word 'Given'

    np_token-act-pair-logits · gpt-4o-mini
    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
     given
    -2.75
    given
    -2.53
     Given
    -2.30
    Given
    -2.23
     GIVEN
    -2.06
     donné
    -1.54
     dado
    -1.41
     diberikan
    -1.34
     dadas
    -1.34
     giv
    -1.30
    POSITIVE LOGITS
    お待ちしております
    0.53
     jScrollPane
    0.45
    supset
    0.45
     jLabel
    0.44
    ustre
    0.43
    արտ
    0.43
    sequently
    0.42
     jButton
    0.41
    canti
    0.41
    architecte
    0.41
    Activations Density 2.649%

    No Known Activations