© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16284
    Prev
    Next
    INDEX
    Explanations

    HTML input tags

    oai_token-act-pair · gemini-2.0-flash

    input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ंदीखरीदारी
    -0.65
     XCTest
    -0.64
     שוליים
    -0.64
    ConstraintMaker
    -0.62
    Према
    -0.58
     BorderRadius
    -0.56
    amerikanischer
    -0.56
     BoxFit
    -0.53
    MessageOf
    -0.53
    DockStyle
    -0.53
    POSITIVE LOGITS
    empêcher
    0.57
    oa̍t
    0.56
    itename
    0.52
    arrête
    0.52
     bör
    0.51
    OfWeek
    0.50
    ilina
    0.48
    flexDirection
    0.48
    cyk
    0.48
    tershire
    0.48
    Activations Density 0.569%

    No Known Activations