© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11923
    Prev
    Next
    INDEX
    Explanations

    various different very common words, and Russian words associated with website forms.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or symbols

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

    w/in

    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
    Sucesor
    -0.56
     barbarians
    -0.52
    ForRow
    -0.52
    estanding
    -0.52
     peasants
    -0.52
     natale
    -0.51
     buckwheat
    -0.50
     bypassing
    -0.50
     sorteo
    -0.50
     laminated
    -0.50
    POSITIVE LOGITS
    ########.
    0.49
     addition
    0.47
    جغرافيا
    0.46
     connection
    0.45
    IGraphics
    0.43
    NameInMap
    0.43
    WillAppear
    0.42
    getDescriptor
    0.42
    KAY
    0.42
     $#
    0.42
    Activations Density 0.789%

    No Known Activations