© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12487
    Prev
    Next
    INDEX
    Explanations

    the word "innovation" and related words

    oai_token-act-pair · gemini-2.0-flash

    innovation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     innovation
    -1.30
     Innovation
    -1.13
    innovation
    -1.13
    Innovation
    -1.09
     innovations
    -1.09
     Innovations
    -1.04
    innov
    -0.98
     INNOV
    -0.94
     Innovative
    -0.92
     innovación
    -0.91
    POSITIVE LOGITS
     surprise
    0.67
    <bos>
    0.64
     shock
    0.62
    Surprise
    0.60
     autorytatywna
    0.59
     الاطلاع
    0.58
     الحره
    0.57
     оригіналу
    0.53
     Shock
    0.52
    Leap
    0.52
    Activations Density 0.978%

    No Known Activations