© 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. 7376
    Prev
    Next
    INDEX
    Explanations

    disjointed non-alphanumeric characters that delimit clauses or provide emphasis

    oai_token-act-pair · gemini-2.0-flash

    technical or specialized terms

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

    Code and documentation snippets

    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
    让我们
    -0.70
    讓我們
    -0.59
     let
    -0.57
    let
    -0.54
    well
    -0.53
     letting
    -0.50
    Well
    -0.49
    Let
    -0.49
    :
    -0.48
     well
    -0.47
    POSITIVE LOGITS
    出版年
    0.91
    Personendaten
    0.85
     AssemblyCulture
    0.83
     Bioaccumulative
    0.81
     Мексичка
    0.80
     referenties
    0.79
    __":
    0.76
     nakalista
    0.75
    AsUp
    0.75
     BoxFit
    0.75
    Activations Density 2.616%

    No Known Activations