© 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. 8493
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with "that" and containing words related to purpose, modality, and causation

    oai_token-act-pair · gemini-2.0-flash

    words and phrases related to strategies and approaches

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

    that

    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
     Italijanski
    -0.80
    脚注の使い方
    -0.68
     Theſe
    -0.67
    StoryboardSegue
    -0.64
     externi
    -0.62
     Мексичка
    -0.62
     itſelf
    -0.61
     {}
    -0.59
     tartalomajánló
    -0.59
     crdi
    -0.59
    POSITIVE LOGITS
     meets
    0.47
     minimize
    0.45
     przypad
    0.44
     minimizes
    0.44
    —
    0.43
     offers
    0.43
    ೇ
    0.43
    Bronnen
    0.43
     will
    0.43
    cetti
    0.42
    Activations Density 2.322%

    No Known Activations