© 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. 16255
    Prev
    Next
    INDEX
    Explanations

    code, variable and data names in programming languages

    oai_token-act-pair · gemini-2.0-flash

    code and datasets

    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
    ModelAdmin
    -0.82
     Garrick
    -0.75
    :✨
    -0.74
    modelBuilder
    -0.73
     للمعارف
    -0.69
     typelib
    -0.68
    GenerationType
    -0.67
    webElementXpaths
    -0.66
    tagHelperRunner
    -0.66
    Composable
    -0.65
    POSITIVE LOGITS
     FRO
    0.69
    custo
    0.66
     Argo
    0.60
     Spro
    0.60
     Legion
    0.59
     Destiny
    0.59
     Elgin
    0.58
     Lili
    0.57
     Dobson
    0.56
     Desai
    0.56
    Activations Density 4.641%

    No Known Activations