© 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. 11731
    Prev
    Next
    INDEX
    Explanations

    the name of a particular organization, Jamii Bora, and words ending in "anga" and the word "rights"

    oai_token-act-pair · gemini-2.0-flash

    words related to entities or titles

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

    Structured information

    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
     Monfieur
    -0.88
     Efq
    -0.87
     Theſe
    -0.78
    !*\
    -0.75
    ंदीखरीदारी
    -0.74
     crdi
    -0.74
     ―――――
    -0.74
     doubtnut
    -0.73
     myſelf
    -0.73
     ſeveral
    -0.71
    POSITIVE LOGITS
     which
    0.75
    which
    0.59
     er
    0.59
     
    0.54
     cui
    0.51
     (
    0.50
     t
    0.49
     bel
    0.49
     whose
    0.49
     S
    0.48
    Activations Density 0.059%

    No Known Activations