© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9505
    Prev
    Next
    INDEX
    Explanations

    technical or scientific words, often related to inventions or processes and sometimes historical dates and people

    oai_token-act-pair · gemini-2.0-flash

    "early"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    béco
    -0.50
    meanor
    -0.42
    enscha
    -0.39
     Longo
    -0.39
    xx
    -0.39
    rrggbb
    -0.38
    Становништво
    -0.37
    يديا
    -0.37
    PostInfinity
    -0.36
    gev
    -0.36
    POSITIVE LOGITS
     early
    2.95
    early
    2.64
    Early
    2.48
     EARLY
    2.41
     Early
    2.34
    EARLY
    2.27
     earliest
    2.27
     frühen
    1.97
    早期
    1.80
     earlier
    1.73
    Activations Density 3.129%

    No Known Activations