© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6133
    Prev
    Next
    INDEX
    Explanations

    words in legal or medical documents that establish terms and conditions

    oai_token-act-pair · gemini-2.0-flash

    phrases related to rules or criteria

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

    defining things

    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
     Monfieur
    -0.84
     Shakspeare
    -0.81
     ſche
    -0.75
     purpoſe
    -0.73
    styleType
    -0.70
     ſeveral
    -0.68
     poffible
    -0.68
    
    -0.68
     Conſ
    -0.68
     myſelf
    -0.66
    POSITIVE LOGITS
     laid
    1.16
     defined
    0.98
     set
    0.94
     established
    0.85
     stated
    0.85
    defined
    0.84
     clearly
    0.84
    laid
    0.81
     lays
    0.79
     fixed
    0.78
    Activations Density 4.119%

    No Known Activations