© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5051
    Prev
    Next
    INDEX
    Explanations

    words and short phrases associated with decisionmaking, changes, and planning

    oai_token-act-pair · gemini-2.0-flash

    say "in"

    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
    IN
    -1.09
    In
    -1.02
     In
    -0.83
    inthe
    -0.74
     IN
    -0.73
    in
    -0.72
    イン
    -0.70
     В
    -0.61
    ın
    -0.60
    into
    -0.59
    POSITIVE LOGITS
    脚注の使い方
    0.69
    StoryboardSegue
    0.59
    hyrchwyd
    0.57
    SourceChecksum
    0.57
    Hentet
    0.52
     Paglinawan
    0.52
    AsUp
    0.51
    RegressionTest
    0.50
    ">//
    0.50
     Diakses
    0.50
    Activations Density 2.218%

    No Known Activations