© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12969
    Prev
    Next
    INDEX
    Explanations

    references to thoughts, ideas, or hypotheses

    oai_token-act-pair · gemini-2.0-flash

    Hypothesis/possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    protoimpl
    -0.50
    yorsunuz
    -0.39
    ólicos
    -0.38
     Air
    -0.38
    digarh
    -0.37
    abilirsiniz
    -0.36
    надцать
    -0.36
    ございました
    -0.36
    ++]=
    -0.36
     %
    -0.35
    POSITIVE LOGITS
     possibilities
    0.85
     onCancelled
    0.78
     possibility
    0.78
    :✨
    0.77
     AppCompatTheme
    0.76
     समीक्षाओं
    0.74
     hunch
    0.70
     Possibilities
    0.69
     bet
    0.69
     theory
    0.69
    Activations Density 4.832%

    No Known Activations