© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5304
    Prev
    Next
    INDEX
    Explanations

    configuration files and programming code snippets

    oai_token-act-pair · gemini-2.0-flash

    affirmative responses

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

    yes

    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
    CONSIN
    -0.50
    richtet
    -0.47
     Dreamer
    -0.45
     bridesmaids
    -0.45
    距
    -0.45
    kwargs
    -0.43
     sức
    -0.42
    cedures
    -0.42
    idue
    -0.42
    annte
    -0.41
    POSITIVE LOGITS
     yes
    1.91
     Yes
    1.77
    Yes
    1.70
    yes
    1.68
     YES
    1.55
    YES
    1.48
     oui
    1.14
     bool
    1.13
    bool
    1.10
     Sì
    1.02
    Activations Density 8.913%

    No Known Activations