© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2108
    Prev
    Next
    INDEX
    Explanations

    the word "per"

    oai_token-act-pair · gemini-2.0-flash

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Distribuzione
    -0.51
     betweenstory
    -0.49
     Вікіпе
    -0.48
    nalité
    -0.47
    orov
    -0.46
    settle
    -0.46
    )_/¯
    -0.45
     relâche
    -0.45
     torno
    -0.44
    attività
    -0.44
    POSITIVE LOGITS
     Percent
    0.69
    
    0.67
     percent
    0.66
    antMatchers
    0.60
    mybatisplus
    0.59
    parsedMessage
    0.59
    ochim
    0.59
    percent
    0.58
    hithe
    0.57
     Prozent
    0.57
    Activations Density 0.172%

    No Known Activations