© 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. 770
    Prev
    Next
    INDEX
    Explanations

    lines of code and the name "Kyutama"

    oai_token-act-pair · gemini-2.0-flash

    Ky

    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
     Bis
    -0.48
     arg
    -0.46
     bis
    -0.44
    espan
    -0.43
    binger
    -0.42
    itag
    -0.41
    lop
    -0.41
    esan
    -0.41
     col
    -0.41
     ô
    -0.40
    POSITIVE LOGITS
    <bos>
    2.50
    الحياه
    1.04
     itſelf
    0.98
     themſelves
    0.96
     purpoſe
    0.93
     raiſ
    0.92
     uſed
    0.91
     pleaſure
    0.90
    ſelves
    0.90
     poffible
    0.90
    Activations Density 8.330%

    No Known Activations