© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    clauses indicating a conditional state or bad situation

    oai_token-act-pair · gemini-2.0-flash

    present participles and gerunds related to permanence or continuity

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

    stay

    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
    الحياه
    -0.65
    parsedMessage
    -0.53
     <>",
    -0.52
    ormány
    -0.50
     Brings
    -0.49
    Personendaten
    -0.48
    ruptedException
    -0.47
    Send
    -0.47
     Bring
    -0.47
     Familienname
    -0.47
    POSITIVE LOGITS
     staying
    1.20
    Staying
    0.94
     Staying
    0.89
    stay
    0.88
     coming
    0.88
     stayed
    0.88
     going
    0.86
     stay
    0.85
     stays
    0.84
     remaining
    0.80
    Activations Density 8.861%

    No Known Activations