© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15047
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Clik
    -0.52
     muligt
    -0.52
    =?";
    -0.50
     allá
    -0.50
     dehors
    -0.50
     dedans
    -0.49
    "],
    -0.48
    (©
    -0.47
     venait
    -0.47
    "){
    -0.47
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.84
     Assyrian
    0.73
     Confucius
    0.67
     metamorphic
    0.67
     Pyongyang
    0.65
     a
    0.64
     which
    0.63
     Polynesian
    0.63
     nomads
    0.63
     Manipur
    0.62
    Activations Density 4.188%

    No Known Activations