© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6220
    Prev
    Next
    INDEX
    Explanations

    the verb "let" or "lets" which is often used to suggest or allow something

    oai_token-act-pair · gemini-2.0-flash

    lets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -
    -1.05
     
    -1.02
    ↵↵
    -1.02
    ,
    -0.94
    '
    -0.91
    ↵
    -0.90
    y
    -0.90
      
    -0.88
    ’
    -0.85
    p
    -0.82
    POSITIVE LOGITS
     فريبيس
    1.59
     Efq
    1.57
    MigrationBuilder
    1.50
     purpoſe
    1.50
    contentLoaded
    1.50
    GEBURTSDATUM
    1.48
     Anſ
    1.48
     myſelf
    1.46
    tvguidetime
    1.46
     ſtate
    1.45
    Activations Density 1.394%

    No Known Activations