© 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. 8625
    Prev
    Next
    INDEX
    Explanations

    descriptions of animals, focusing on physical attributes and eating habits.

    oai_token-act-pair · gemini-2.0-flash

    Anatomy and biology

    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
     Tu
    -0.48
     G
    -0.47
     T
    -0.47
     Al
    -0.46
     Am
    -0.46
     le
    -0.46
     
    -0.44
     L
    -0.44
     å
    -0.43
     vi
    -0.43
    POSITIVE LOGITS
     myſelf
    1.34
     pleaſure
    1.22
     houſe
    1.21
     Houſe
    1.21
     Majefty
    1.17
     Monfieur
    1.13
     purpoſe
    1.11
     ſche
    1.11
     Jefus
    1.10
     greateſt
    1.10
    Activations Density 3.031%

    No Known Activations