© 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. 888
    Prev
    Next
    INDEX
    Explanations

    words relating to time, numbers and code

    oai_token-act-pair · gemini-2.0-flash

    Code and chat 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
     betweenstory
    -0.66
     CreateTagHelper
    -0.65
     nî
    -0.60
    rinfo
    -0.57
     Audiodateien
    -0.55
    webElement
    -0.53
    الدراسه
    -0.50
     Nare
    -0.49
     typhoid
    -0.48
    MessageTagHelper
    -0.48
    POSITIVE LOGITS
    ans
    0.59
    e
    0.55
     ans
    0.55
    atguigu
    0.53
    migrationBuilder
    0.52
    esModule
    0.50
    *>(
    0.50
    出版年
    0.48
    μός
    0.48
    nestjs
    0.47
    Activations Density 5.863%

    No Known Activations