© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6646
    Prev
    Next
    INDEX
    Explanations

    occurrences of someone explaining something.

    oai_token-act-pair · gemini-2.0-flash

    mean

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ally
    -0.41
    thin
    -0.41
    them
    -0.40
     kohta
    -0.38
     lesquels
    -0.37
     Comentarios
    -0.36
    Them
    -0.36
     quedado
    -0.35
     czym
    -0.34
     jus
    -0.33
    POSITIVE LOGITS
     ModelExpression
    1.05
    tvguidetime
    1.01
     that
    0.98
    TypedDataSet
    0.95
    ]")]
    0.87
     चीज़ों
    0.87
     we
    0.85
    parsedMessage
    0.84
    íncia
    0.81
    ThroughAttribute
    0.79
    Activations Density 1.531%

    No Known Activations