© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13825
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" followed by other words.

    oai_token-act-pair · gemini-2.0-flash

    understanding what's going on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     what
    -0.85
    what
    -0.72
     What
    -0.66
    What
    -0.64
     whom
    -0.60
    WHAT
    -0.60
     how
    -0.59
     WHAT
    -0.59
    何
    -0.59
     cosa
    -0.55
    POSITIVE LOGITS
    __(/*!
    0.73
    oa̍t
    0.68
     فريبيس
    0.65
     HasFactory
    0.65
    GraphicsUnit
    0.62
    CodeAttribute
    0.62
    InstanceState
    0.62
    SharedCtor
    0.62
    ✷
    0.60
    interopRequire
    0.58
    Activations Density 1.045%

    No Known Activations