© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    a variety of programming language constructs, likely javascript, including assignment operators, equality checks, logical operators, and array declarations

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    forChild
    -0.77
     disambiguazione
    -0.76
     autorytatywna
    -0.73
    Discography
    -0.72
    تقاوى
    -0.71
    migrationBuilder
    -0.67
    :✨
    -0.66
    CppMethod
    -0.64
    EMPLOY
    -0.63
    UserScript
    -0.61
    POSITIVE LOGITS
    v
    0.63
    z
    0.60
    k
    0.59
    p
    0.54
    Ge
    0.54
    T
    0.53
    x
    0.53
    Z
    0.52
    S
    0.52
    b
    0.52
    Activations Density 7.707%

    No Known Activations