© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10017
    Prev
    Next
    INDEX
    Explanations

    instances of lacking financial means, often using the word afford/cannot

    oai_token-act-pair · gemini-2.0-flash

    afford

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     <<<<<<<<<<<<<<
    -0.90
     resourceCulture
    -0.87
    ="@+
    -0.77
    RegressionTest
    -0.77
     referenties
    -0.76
     تضيفلها
    -0.75
    __':
    -0.72
    __":
    -0.72
    httphttps
    -0.72
    دانشنامهٔ
    -0.71
    POSITIVE LOGITS
    ブリッド
    0.51
     ilan
    0.48
    зву
    0.46
    mota
    0.46
    culosis
    0.46
    P
    0.46
     Bedürfn
    0.44
    rmdir
    0.44
     rejoice
    0.44
    หว
    0.44
    Activations Density 1.027%

    No Known Activations