© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11792
    Prev
    Next
    INDEX
    Explanations

    discussions of climate change

    oai_token-act-pair · gemini-2.0-flash

    change

    np_max-act · gemini-2.0-flash

    change

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     chofe
    -0.91
     ―――――
    -0.90
     Anſ
    -0.90
     Theſe
    -0.89
     raiſ
    -0.88
     itſelf
    -0.87
     ſeveral
    -0.86
    <bos>
    -0.83
     poffible
    -0.83
     leaſt
    -0.83
    POSITIVE LOGITS
     (
    0.57
      
    0.56
     assim
    0.55
    himself
    0.51
    ↵
    0.51
    Myself
    0.50
     /
    0.50
    mitglied
    0.50
     //
    0.49
    WriteBarrier
    0.48
    Activations Density 0.394%

    No Known Activations