© 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. 6407
    Prev
    Next
    INDEX
    Explanations

    code, and especially long lines of hyphens broken up by #'s

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    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
     originales
    -0.73
    Personensuche
    -0.69
     originais
    -0.69
    original
    -0.68
     original
    -0.67
    Original
    -0.67
     ostavi
    -0.64
     originali
    -0.62
     Original
    -0.61
     originale
    -0.60
    POSITIVE LOGITS
    WillAppear
    0.59
    clable
    0.52
    ElementException
    0.51
     Tit
    0.50
    XMLSchema
    0.50
     Publication
    0.49
     незавершена
    0.49
    الثة
    0.48
    LayoutStyle
    0.48
     iſt
    0.47
    Activations Density 8.901%

    No Known Activations