© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12628
    Prev
    Next
    INDEX
    Explanations

    words and names associated with criminals and the police

    oai_token-act-pair · gemini-2.0-flash

    references to specific individuals and legal contexts

    np_token-act-pair-logits · gpt-4o-mini

    legal proceedings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.67
    GTCX
    -0.64
    parsedMessage
    -0.61
    RenderAtEndOf
    -0.61
     cdti
    -0.61
    DoubleQuotes
    -0.60
     CreateTagHelper
    -0.60
    NOPQRST
    -0.60
     ERSITY
    -0.57
    merkt
    -0.56
    POSITIVE LOGITS
    曲
    0.47
     ervan
    0.47
    \]
    0.46
     صوتيه
    0.45
     appeared
    0.45
     denied
    0.44
     adam
    0.44
     lived
    0.43
     Denied
    0.43
    0.43
    Activations Density 3.035%

    No Known Activations