© 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. 9997
    Prev
    Next
    INDEX
    Explanations

    the word "according" and words that are short prefixes used in academic writing

    oai_token-act-pair · gemini-2.0-flash

    According

    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
    DockStyle
    -0.75
     فريبيس
    -0.72
    surgery
    -0.71
    muscular
    -0.71
    IRECT
    -0.66
    ônico
    -0.65
     "..\..\
    -0.65
    ]')
    -0.65
     مشين
    -0.65
    Datuak
    -0.65
    POSITIVE LOGITS
    ’
    0.59
    let
    0.58
    try
    0.54
    ing
    0.50
    al
    0.50
    '
    0.50
    ho
    0.49
    print
    0.49
     oc
    0.49
    Let
    0.48
    Activations Density 1.834%

    No Known Activations