© 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. 14456
    Prev
    Next
    INDEX
    Explanations

    mentions of studies and related phrases

    oai_token-act-pair · gemini-2.0-flash

    scholarly studies

    np_max-act · gemini-2.0-flash
    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
    ↵↵
    -0.59
    TabIndex
    -0.52
     section
    -0.51
    2
    -0.50
     dayan
    -0.50
    ’
    -0.50
     Instead
    -0.50
    .
    -0.50
     rather
    -0.49
     instead
    -0.49
    POSITIVE LOGITS
     nakalista
    1.04
     мәкал
    0.95
    IntoConstraints
    0.84
     Roskov
    0.83
    følgelig
    0.83
    contentLoaded
    0.82
    UserScript
    0.82
     متعلقه
    0.80
     Daß
    0.79
     kasarigan
    0.78
    Activations Density 0.667%

    No Known Activations