© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15914
    Prev
    Next
    INDEX
    Explanations

    danish text including references to dates

    oai_token-act-pair · gemini-2.0-flash

    Non-English languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ⓧ
    -0.98
     للمعارف
    -0.93
     <<<<<<<<<<<<<<
    -0.84
    adaptiveStyles
    -0.78
     متعلقه
    -0.76
    ValueStyle
    -0.72
     houſe
    -0.72
    Datuak
    -0.71
    NameInMap
    -0.70
     שוליים
    -0.70
    POSITIVE LOGITS
     da
    0.57
     e
    0.50
     i
    0.50
     at
    0.48
     et
    0.48
     på
    0.46
     is
    0.43
     og
    0.41
     u
    0.40
     pre
    0.39
    Activations Density 0.126%

    No Known Activations