© 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. 412
    Prev
    Next
    INDEX
    Explanations

    code snippets, often containing javascript or other programming language syntax

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    .
    -0.38
    ,
    -0.33
     códigos
    -0.31
     specchio
    -0.31
     télécharge
    -0.31
     mecanismos
    -0.30
     círculos
    -0.29
     rayures
    -0.29
     módulos
    -0.29
     boî
    -0.28
    POSITIVE LOGITS
     myſelf
    0.84
     whoſe
    0.79
     himſelf
    0.76
     becauſe
    0.75
     ſhe
    0.75
     ſeveral
    0.73
     itſelf
    0.73
     poffe
    0.73
     Efq
    0.73
     houſe
    0.71
    Activations Density 10.249%

    No Known Activations