© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9173
    Prev
    Next
    INDEX
    Explanations

    words and phrases ending in "ed" that have to do with communicating information

    oai_token-act-pair · gemini-2.0-flash

    past tense forms

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

    technical data

    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
    parsedMessage
    -1.14
     extracted
    -1.02
     raiſ
    -0.96
     brewed
    -0.94
     edited
    -0.93
     filmed
    -0.92
     subtracted
    -0.91
     sequenced
    -0.90
     rendered
    -0.90
     mined
    -0.90
    POSITIVE LOGITS
     Had
    0.46
    didn
    0.42
     Were
    0.41
     write
    0.40
     Auf
    0.40
    Had
    0.40
    Didn
    0.40
    were
    0.40
     Did
    0.39
    grew
    0.39
    Activations Density 4.300%

    No Known Activations