© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15380
    Prev
    Next
    INDEX
    Explanations

    words and names ending in "est" or "ext."

    oai_token-act-pair · gemini-2.0-flash

    est

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵
    -1.03
    /
    -1.01
     
    -0.96
     “
    -0.95
    _
    -0.89
    -
    -0.88
     (
    -0.87
     or
    -0.86
     \
    -0.81
    ’
    -0.81
    POSITIVE LOGITS
     itſelf
    1.77
     Efq
    1.73
     myſelf
    1.73
     ―――――
    1.62
     Reſ
    1.60
     ་་
    1.59
     Theſe
    1.59
     Anſ
    1.59
     disambiguazione
    1.58
     doubtnut
    1.57
    Activations Density 4.555%

    No Known Activations