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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 652
    Prev
    Next
    INDEX
    Explanations

    references to the recent past

    oai_token-act-pair · gemini-2.0-flash

    last/past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    couple
    -0.84
     nahilalakip
    -0.81
     couple
    -0.77
     >=",
    -0.72
    PasswordEncoder
    -0.71
     $_"
    -0.70
     endregion
    -0.70
     itſelf
    -0.69
    Koordinaten
    -0.69
     Anſ
    -0.69
    POSITIVE LOGITS
     
    0.58
     x
    0.54
     six
    0.50
     five
    0.45
     seven
    0.45
     eight
    0.43
     nine
    0.42
     four
    0.42
     s
    0.42
     many
    0.38
    Activations Density 5.218%

    No Known Activations