© 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. 9264
    Prev
    Next
    INDEX
    Explanations

    descriptions of human touch, especially between people

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code-related syntax

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

    hand and arm actions

    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
    ArrowToggle
    -0.77
     fillings
    -0.57
     kaarangay
    -0.56
    WithIOException
    -0.54
    statt
    -0.50
    contentLoaded
    -0.50
    unehmen
    -0.49
     unfore
    -0.48
    viert
    -0.47
    Inhalte
    -0.46
    POSITIVE LOGITS
     Normdatei
    0.62
    AndEndTag
    0.59
    keyColumn
    0.54
    DrawerToggle
    0.50
    Assured
    0.50
    畿
    0.49
    raging
    0.48
     LayoutInflater
    0.48
    /*-
    0.48
     enda
    0.47
    Activations Density 0.428%

    No Known Activations