© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6393
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     myſelf
    -0.86
    دانشنامهٔ
    -0.85
    ValueStyle
    -0.85
     fubject
    -0.79
     itſelf
    -0.79
     ainfi
    -0.75
     ſtate
    -0.75
    tvguidetime
    -0.75
     ſche
    -0.74
     himſelf
    -0.73
    POSITIVE LOGITS
     भ
    0.51
     long
    0.51
     по
    0.50
    vő
    0.46
     ge
    0.46
    Booth
    0.45
    chas
    0.45
     esp
    0.44
     biến
    0.44
     hand
    0.44
    Activations Density 0.527%

    No Known Activations