© 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. 2143
    Prev
    Next
    INDEX
    Explanations

    words that refer to long physical objects or lengths

    oai_token-act-pair · gemini-2.0-flash

    longer/long

    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
    NOPQRST
    -0.85
    mybatisplus
    -0.84
     CreateTagHelper
    -0.82
     Paglinawan
    -0.80
     otomatig
    -0.76
     utafitiHapana
    -0.75
     propOrder
    -0.74
     ujednoznacz
    -0.74
     calendriers
    -0.74
     BoxFit
    -0.72
    POSITIVE LOGITS
    agissait
    0.42
    헌
    0.41
     ${
    0.41
    oned
    0.40
     die
    0.39
     colazione
    0.39
    capacidad
    0.38
    ola
    0.38
    mbo
    0.37
    date
    0.36
    Activations Density 14.957%

    No Known Activations