© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9015
    Prev
    Next
    INDEX
    Explanations

    lines of code

    oai_token-act-pair · gemini-2.0-flash

    8

    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
    -
    -0.57
    .
    -0.53
    <eos>
    -0.49
     ,
    -0.49
    ant
    -0.48
    ian
    -0.48
     .
    -0.47
    .,
    -0.46
    ia
    -0.46
     form
    -0.46
    POSITIVE LOGITS
     Савезне
    0.84
     незавершена
    0.83
     MainAxisSize
    0.81
     Roskov
    0.78
    mybatisplus
    0.78
    migrationBuilder
    0.76
    principalColumn
    0.75
     isInitialized
    0.75
    Życiorys
    0.74
    writeField
    0.74
    Activations Density 3.028%

    No Known Activations