© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    HTML tags and some related attributes

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    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
     Efq
    -1.16
     purpoſe
    -1.10
     ſtate
    -1.03
     cauſe
    -1.02
     houſe
    -0.99
     beſt
    -0.98
     caufe
    -0.96
     pleaſure
    -0.96
     ftate
    -0.94
     Shakspeare
    -0.94
    POSITIVE LOGITS
    ><!--
    0.43
     "..\..\
    0.40
    "
    0.39
    enumi
    0.37
    )
    0.37
     mathvariant
    0.36
     t
    0.36
     "..\..\..\
    0.35
     о
    0.35
     AT
    0.34
    Activations Density 0.996%

    No Known Activations