© 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. 15066
    Prev
    Next
    INDEX
    Explanations

    the word "core" and words appearing near it

    oai_token-act-pair · gemini-2.0-flash

    terms related to "core" in technical contexts

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

    core

    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
     createState
    -0.56
    BindView
    -0.53
    Américaine
    -0.52
    dighet
    -0.50
    لفل
    -0.49
    lave
    -0.48
     far
    -0.47
    ([...
    -0.47
    clyde
    -0.46
    Legături
    -0.46
    POSITIVE LOGITS
     otomatig
    0.63
    WebVitals
    0.57
     linkovi
    0.55
    parsedMessage
    0.55
     للاسماء
    0.54
     vulgaires
    0.53
     RMA
    0.51
    Autoritní
    0.50
     Gén
    0.50
    IndentedString
    0.49
    Activations Density 1.567%

    No Known Activations