© 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. 16294
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to thread management and stack traces, possibly in Java

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
    tvguidetime
    -0.78
     оригіналу
    -0.74
    Bibliograf
    -0.73
    SourceChecksum
    -0.72
     newOwner
    -0.72
    interopRequire
    -0.71
    DebuggerStep
    -0.69
     estekak
    -0.69
     NavController
    -0.69
    AndroidJUnit
    -0.68
    POSITIVE LOGITS
    ={{
    0.43
    /*---
    0.40
     urbanas
    0.39
    wa
    0.38
    ko
    0.38
    نيف
    0.36
    deo
    0.35
    0.35
     ==========
    0.35
    orszá
    0.34
    Activations Density 0.152%

    No Known Activations