© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15086
    Prev
    Next
    INDEX
    Explanations

    the article "a" or "an" followed by a noun

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -0.61
    </blockquote>
    -0.58
    ”.
    -0.56
    i
    -0.54
    ho
    -0.54
    à
    -0.52
    ?”
    -0.51
    .”
    -0.51
    q
    -0.51
    z
    -0.51
    POSITIVE LOGITS
     Monfieur
    1.05
     myſelf
    0.91
     Eſ
    0.87
     Anſ
    0.87
     Efq
    0.84
    eradish
    0.82
    polation
    0.81
    bibfield
    0.81
     Reſ
    0.79
     becauſe
    0.77
    Activations Density 1.199%

    No Known Activations