© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6621
    Prev
    Next
    INDEX
    Explanations

    the word "early"

    oai_token-act-pair · gemini-2.0-flash

    early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     early
    -2.73
    early
    -2.63
    Early
    -2.48
     Early
    -2.39
     EARLY
    -2.30
    EARLY
    -2.11
     frühen
    -1.84
     vroe
    -1.56
    早期
    -1.53
     late
    -1.37
    POSITIVE LOGITS
    romyalgia
    0.56
     worse
    0.56
    ORCID
    0.55
    ContextHolder
    0.54
    ritsar
    0.53
     higher
    0.52
    sonian
    0.51
    tiek
    0.51
    htaccess
    0.50
    AGR
    0.49
    Activations Density 0.472%

    No Known Activations