© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14087
    Prev
    Next
    INDEX
    Explanations

    words that begin with "pre-" or are related to precursors in scientific notation and technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Pre
    -2.91
     pre
    -2.89
    Pre
    -2.86
    pre
    -2.64
     PRE
    -2.47
    PRE
    -2.39
     pré
    -2.30
     pres
    -2.08
     Pres
    -2.03
     Pré
    -1.99
    POSITIVE LOGITS
     Efq
    0.65
     auffi
    0.59
     pleaſure
    0.58
    RenderAtEndOf
    0.56
     ―――――
    0.56
     canina
    0.56
     Monfieur
    0.55
     Theſe
    0.55
     faſt
    0.55
     Anſ
    0.55
    Activations Density 3.670%

    No Known Activations