© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10579
    Prev
    Next
    INDEX
    Explanations

    the word "back" as a standalone word or as part of a compound word

    oai_token-act-pair · gemini-2.0-flash

    back

    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
    addPreferredGap
    -0.69
    protoimpl
    -0.64
    ValueStyle
    -0.62
    PerformLayout
    -0.56
    addGap
    -0.56
    nthetic
    -0.51
    principalTable
    -0.51
     AssemblyCulture
    -0.50
    stackSize
    -0.49
     arşivlendi
    -0.49
    POSITIVE LOGITS
    曖昧さ回避
    0.58
     كومونز
    0.54
    Literatuur
    0.50
    yethyl
    0.49
    الإنجليزية
    0.49
    chequer
    0.49
     classé
    0.49
    ronym
    0.49
     vectorielles
    0.48
    lapi
    0.48
    Activations Density 1.110%

    No Known Activations