© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12623
    Prev
    Next
    INDEX
    Explanations

    questions and relative pronouns along with related adjectives

    oai_token-act-pair · gemini-2.0-flash

    Which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Which
    -1.32
    Which
    -1.17
     Who
    -1.12
     Where
    -1.01
    Who
    -0.94
     What
    -0.93
    Where
    -0.84
     Why
    -0.82
     How
    -0.77
    What
    -0.73
    POSITIVE LOGITS
    elemField
    0.77
    ThroughAttribute
    0.72
    UnusedPrivate
    0.65
    RenderAtEndOf
    0.65
     Egli
    0.65
    EndProject
    0.64
    FunctionFlags
    0.64
     Référence
    0.63
    Hochspringen
    0.63
    ModelBuilder
    0.62
    Activations Density 3.789%

    No Known Activations