© 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. 11884
    Prev
    Next
    INDEX
    Explanations

    scientific text primarily about fatty acids and oxidation

    oai_token-act-pair · gemini-2.0-flash

    insulin and metabolism

    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
    tvguidetime
    -0.75
    endphp
    -0.73
    发表于
    -0.71
    دانشنامهٔ
    -0.70
     ―――――
    -0.69
     RSSSF
    -0.68
     EKG
    -0.67
     Shakspeare
    -0.67
    StoryboardSegue
    -0.67
     constitutions
    -0.65
    POSITIVE LOGITS
     tre
    0.47
    State
    0.43
    原始内容存档
    0.43
    ü
    0.40
     Or
    0.40
     peng
    0.39
    Zaj
    0.39
    בי
    0.39
     tré
    0.39
     Stamm
    0.38
    Activations Density 3.861%

    No Known Activations