© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9365
    Prev
    Next
    INDEX
    Explanations

    statements containing speech or thoughts

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    J
    -0.50
    j
    -0.45
    1
    -0.43
    awtextra
    -0.42
    z
    -0.41
    f
    -0.40
    B
    -0.40
    c
    -0.39
    U
    -0.38
    3
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.87
    />";
    0.82
    ChildScrollView
    0.78
     tartalomajánló
    0.77
    adeloupe
    0.77
     ویکی‌آمباردا
    0.77
    Referanser
    0.77
    ]")]
    0.76
    JspWriter
    0.76
     $_"
    0.75
    Activations Density 12.338%

    No Known Activations