© 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. 4110
    Prev
    Next
    INDEX
    Explanations

    medical findings about the treatments of depression, anxiety and fatigue

    oai_token-act-pair · gemini-2.0-flash

    Science/technical

    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
     DT
    -0.93
     Ml
    -0.92
     cm
    -0.92
     ml
    -0.91
     lt
    -0.91
     nm
    -0.90
     pt
    -0.90
     MM
    -0.90
     ML
    -0.90
     ls
    -0.90
    POSITIVE LOGITS
    تفصیلات
    0.64
     >=",
    0.59
     MonoBehaviour
    0.57
    scriptcase
    0.56
    Климат
    0.53
    cellaneous
    0.53
     Leverkusen
    0.49
    下载附件
    0.49
     textStatus
    0.48
     RoutedEventArgs
    0.48
    Activations Density 10.323%

    No Known Activations