© 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. 12820
    Prev
    Next
    INDEX
    Explanations

    aperiodic and seemingly unrelated words.

    oai_token-act-pair · gemini-2.0-flash

    unusual text snippets

    np_max-act · gemini-2.0-flash

    foreign words

    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
    ſelf
    -0.85
    OrWhiteSpace
    -0.78
    ResumeLayout
    -0.74
    ISupport
    -0.73
    onViewCreated
    -0.72
    soever
    -0.69
     AssemblyTitle
    -0.68
    HomeAsUpEnabled
    -0.66
    CardHeader
    -0.66
    ophenyl
    -0.66
    POSITIVE LOGITS
    îtra
    0.70
    Moc
    0.67
     remarqu
    0.64
     namelijk
    0.63
     voks
    0.62
     nemlig
    0.60
     piú
    0.60
     vuoto
    0.59
    άσ
    0.59
    Adress
    0.59
    Activations Density 15.361%

    No Known Activations