© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7765
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain references to keys and variable types

    oai_token-act-pair · gemini-2.0-flash

    key

    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
    بوابة
    -0.54
    äj
    -0.52
    gypti
    -0.50
    대로
    -0.50
     impar
    -0.49
    Tembelea
    -0.49
    spotify
    -0.49
     Friendly
    -0.47
     disapproved
    -0.46
    хозяй
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.65
     referenties
    0.64
     consultato
    0.63
    SequentialGroup
    0.62
    脚注の使い方
    0.60
     endfor
    0.57
    MergeFrom
    0.57
    consulté
    0.56
     Normdatei
    0.56
    enumii
    0.53
    Activations Density 2.204%

    No Known Activations