© 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. 14490
    Prev
    Next
    INDEX
    Explanations

    the word "looking"

    oai_token-act-pair · gemini-2.0-flash

    search queries

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

    looking

    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
     TestBed
    -0.85
     onOptions
    -0.79
    ftagPool
    -0.71
    enderror
    -0.70
    kegaard
    -0.68
    VersionUID
    -0.68
    RegressionTest
    -0.66
    WireFormatLite
    -0.65
    ChildScrollView
    -0.65
     looked
    -0.65
    POSITIVE LOGITS
     for
    1.05
     pentru
    0.66
    for
    0.64
     για
    0.62
     для
    0.59
     tensione
    0.55
    pentru
    0.55
     voor
    0.55
     destinés
    0.55
     för
    0.54
    Activations Density 0.383%

    No Known Activations