© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    the phrase "a wide range of" or similar

    oai_token-act-pair · gemini-2.0-flash

    variety/diversity/breadth

    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
     wide
    -1.49
     Wide
    -1.40
    Wide
    -1.21
     WIDE
    -1.21
    wide
    -1.14
    WIDE
    -1.04
     wider
    -0.89
     widest
    -0.87
     broad
    -0.87
     широкий
    -0.78
    POSITIVE LOGITS
    TagMode
    0.74
     StringVar
    0.64
     kasarigan
    0.63
    DebuggerNonUser
    0.62
    ValueStyle
    0.60
     PackageManager
    0.60
    +:+
    0.59
    MigrationBuilder
    0.58
    Życiorys
    0.58
    TProtocol
    0.55
    Activations Density 2.975%

    No Known Activations