© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10799
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases that indicate speculation, recent information, or changes over time.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    StoryboardSegue
    -0.75
     ostavi
    -0.65
     NUKAT
    -0.65
    قایناق‌لار
    -0.61
     pié
    -0.58
     surla
    -0.58
    principalColumn
    -0.58
     forthcoming
    -0.57
     صوتيه
    -0.57
     <=",
    -0.57
    POSITIVE LOGITS
     itſelf
    0.54
     Pues
    0.50
     Portanto
    0.49
     Tienen
    0.49
     Encuentra
    0.48
     houſe
    0.47
     Ubicación
    0.47
     themſelves
    0.47
     бывает
    0.46
    attaa
    0.46
    Activations Density 6.529%

    No Known Activations