© 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. 6424
    Prev
    Next
    INDEX
    Explanations

    text from internet comments, code, and transcripts represented with a variety of punctuation

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or concepts

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

    informal blog or code text

    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
    nicze
    -0.59
     Gew
    -0.59
    ?}
    -0.54
    .}
    -0.54
    中华人民共和国
    -0.53
    bull
    -0.51
    isNull
    -0.51
     Brown
    -0.50
    τεύ
    -0.50
     Bull
    -0.50
    POSITIVE LOGITS
     ErrIntOverflow
    0.77
    RegistryLite
    0.63
    expandindo
    0.60
    RUnlock
    0.57
    __':
    0.57
     متعلقه
    0.56
    setVerticalGroup
    0.55
     saites
    0.55
    <_>
    0.54
    PullParser
    0.53
    Activations Density 9.295%

    No Known Activations