© 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. 2936
    Prev
    Next
    INDEX
    Explanations

    text describing scientific calculations and parameters for those calculations

    oai_token-act-pair · gemini-2.0-flash

    Scientific texts

    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
    twimg
    -0.75
     AssemblyTitle
    -0.68
    abestanden
    -0.68
     ddelweddau
    -0.65
    期刊论文
    -0.62
    EndInit
    -0.61
    सन्दर्भ
    -0.60
     continúas
    -0.60
    aloo
    -0.60
    HtmlAttribute
    -0.59
    POSITIVE LOGITS
    fromnode
    0.42
     sarana
    0.41
     T
    0.40
    koľvek
    0.39
    cagon
    0.37
    tonode
    0.35
     investigação
    0.35
     Turn
    0.35
    Turn
    0.34
    خار
    0.34
    Activations Density 3.392%

    No Known Activations