© 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. 9636
    Prev
    Next
    INDEX
    Explanations

    words related to frozen water and chilled food storage

    oai_token-act-pair · gemini-2.0-flash

    specific technical terms or jargon

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

    cold temperatures

    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
    +:+
    -0.68
     initComponents
    -0.53
    OOC
    -0.49
     الحره
    -0.48
    клопе
    -0.48
     progra
    -0.47
     Journals
    -0.44
    Noter
    -0.44
    TProtocol
    -0.43
     bandeau
    -0.42
    POSITIVE LOGITS
    Sklici
    0.58
    SafeMath
    0.58
     henvisninger
    0.57
    μιουργ
    0.57
    TagMode
    0.56
     ddelweddau
    0.52
     Rine
    0.52
     HttpNotFound
    0.52
    Pfalz
    0.50
    Literatur
    0.49
    Activations Density 2.975%

    No Known Activations