© 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. 4509
    Prev
    Next
    INDEX
    Explanations

    conjunctions in complex sentences

    oai_token-act-pair · gemini-2.0-flash

    simple phrases or expressions

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

    say "the more, the more"

    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
    rawDesc
    -0.65
    __(/*!
    -0.63
    ⓧ
    -0.59
     CURIAM
    -0.59
    jspx
    -0.56
    awtextra
    -0.56
     विश्वसनीयता
    -0.55
    Pyx
    -0.53
     jspb
    -0.53
    jsdelivr
    -0.50
    POSITIVE LOGITS
     the
    1.64
     enfans
    0.59
     την
    0.59
     kív
    0.58
    the
    0.58
    tothe
    0.56
     roulant
    0.55
    ofthe
    0.52
     ofthe
    0.52
    etna
    0.50
    Activations Density 2.760%

    No Known Activations