© 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. 8607
    Prev
    Next
    INDEX
    Explanations

    references to money and costs

    oai_token-act-pair · gemini-2.0-flash

    ticket prices and sales information

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

    Prices

    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
    adaptiveStyles
    -0.88
     autorytatywna
    -0.79
    mobileqq
    -0.78
    MigrationBuilder
    -0.78
    SequentialGroup
    -0.78
    CompleteListener
    -0.76
    styleType
    -0.75
     Roskov
    -0.75
    Tembelea
    -0.72
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
    .
    0.50
     Walkover
    0.46
    UnusedPrivate
    0.46
     fört
    0.45
    base
    0.37
    arsal
    0.37
     PBS
    0.37
    ayuno
    0.37
    -
    0.36
     Audiodateien
    0.36
    Activations Density 6.494%

    No Known Activations