© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13391
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "enter" that indicate a formal undertaking or legal/official action

    oai_token-act-pair · gemini-2.0-flash

    entered

    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
    Negative Logits
    ↵↵
    -0.64
    <strong>
    -0.60
    <bos>
    -0.58
     
    -0.57
    <h2>
    -0.53
     was
    -0.52
    ↵
    -0.50
    </strong>
    -0.50
     good
    -0.49
    <h4>
    -0.48
    POSITIVE LOGITS
     resourceCulture
    0.87
     صوتيه
    0.85
     authorisation
    0.82
    SharedDtor
    0.82
     EconPapers
    0.82
     &___
    0.82
    complexContent
    0.82
    IndentedString
    0.82
     visualiser
    0.82
     optimised
    0.82
    Activations Density 1.224%

    No Known Activations