© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    specifically defined terms and equations

    oai_token-act-pair · gemini-2.0-flash

    phrases related to definitions and mathematical expressions

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

    defined

    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
    UnknownFieldSet
    -0.60
    lité
    -0.54
    StreetMap
    -0.53
    isante
    -0.52
     oock
    -0.51
    evident
    -0.51
    湃
    -0.50
    backers
    -0.50
     Companion
    -0.50
    λισ
    -0.50
    POSITIVE LOGITS
     as
    0.67
    DockStyle
    0.52
    adaptiveStyles
    0.52
    TemporalType
    0.48
     by
    0.48
     tématu
    0.47
     MainAxisSize
    0.47
    LoadScene
    0.47
    ритори
    0.46
     using
    0.46
    Activations Density 3.184%

    No Known Activations