© 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. 9323
    Prev
    Next
    INDEX
    Explanations

    phrases related to asking for help or giving instructions

    oai_token-act-pair · gemini-2.0-flash

    asking for questions

    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
     réflexion
    -0.47
     amostra
    -0.47
     känna
    -0.47
     puisse
    -0.45
    锆
    -0.44
     perla
    -0.43
     curieux
    -0.43
     Información
    -0.43
     puissent
    -0.42
    categorical
    -0.41
    POSITIVE LOGITS
     JpaRepository
    0.75
    TagMode
    0.69
     فريبيس
    0.67
     AssemblyTitle
    0.65
    Aiheesta
    0.64
    ########.
    0.63
    المناصب
    0.59
     createContext
    0.57
    eleste
    0.56
    UnifiedTopology
    0.56
    Activations Density 9.451%

    No Known Activations