© 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. 8656
    Prev
    Next
    INDEX
    Explanations

    instances of programming code and mathematical articles

    oai_token-act-pair · gemini-2.0-flash

    say "const"

    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
    const
    -1.88
    Const
    -1.84
     Constant
    -1.82
     constants
    -1.77
     const
    -1.77
     Const
    -1.74
    constant
    -1.73
    Constant
    -1.73
     Constants
    -1.72
     constant
    -1.65
    POSITIVE LOGITS
    kia
    0.42
    قاب
    0.40
    taobao
    0.39
     اح
    0.39
    metz
    0.39
    FunctionFlags
    0.39
    ören
    0.38
    ‌آم
    0.38
    lando
    0.38
    یت
    0.38
    Activations Density 1.499%

    No Known Activations