© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12918
    Prev
    Next
    INDEX
    Explanations

    code blocks with curly braces in a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.50
     OnInit
    -0.44
    PRWEB
    -0.43
     /\.(
    -0.43
    IsInitialized
    -0.41
    igne
    -0.39
    umin
    -0.39
    ôt
    -0.39
    XMLSchema
    -0.38
    NgModule
    -0.38
    POSITIVE LOGITS
     umane
    0.35
    felves
    0.33
     themſelves
    0.32
     purpoſe
    0.32
     umana
    0.32
     humaines
    0.32
     собою
    0.31
     ftate
    0.30
     steder
    0.30
     humanas
    0.29
    Activations Density 0.682%

    No Known Activations