© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5921
    Prev
    Next
    INDEX
    Explanations

    the word "processing" and words in the same context, like "processor".

    oai_token-act-pair · gemini-2.0-flash

    processing

    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
    ally
    -0.84
    ing
    -0.67
    __*/
    -0.65
    if
    -0.63
    to
    -0.63
    le
    -0.63
    ale
    -0.59
    ib
    -0.59
     jeunesse
    -0.58
    ’
    -0.57
    POSITIVE LOGITS
     InputDecoration
    1.02
    SourceChecksum
    0.90
    ugeot
    0.88
    jectures
    0.88
    NUMX
    0.88
    athread
    0.85
     Efq
    0.84
    endgroup
    0.84
     noDo
    0.84
    andafter
    0.83
    Activations Density 1.618%

    No Known Activations