© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16038
    Prev
    Next
    INDEX
    Explanations

    phrases that contain words like "can", "help", and "will"

    oai_token-act-pair · gemini-2.0-flash

    asking for assistance

    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
    Helping
    -0.77
     Helping
    -0.76
     helping
    -0.74
    WithIOException
    -0.68
     Helps
    -0.67
    helping
    -0.67
    Helps
    -0.66
    uxxxx
    -0.65
     helps
    -0.62
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
    脚注の使い方
    0.99
     NSCoder
    0.75
     polling
    0.55
     memoized
    0.55
    ebilir
    0.52
    duled
    0.51
     nahilalakip
    0.51
     clear
    0.51
    GIVEREF
    0.51
    AddHtmlAttribute
    0.50
    Activations Density 7.089%

    No Known Activations