© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4830
    Prev
    Next
    INDEX
    Explanations

    common conversational words that setup clauses or connect ideas.

    oai_token-act-pair · gemini-2.0-flash

    quantifiers indicating quantity

    np_token-act-pair-logits · gpt-4o-mini

    many

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    teer
    -0.44
    белый
    -0.42
    outh
    -0.41
     elevación
    -0.41
    后者
    -0.41
     gouvernements
    -0.41
    plak
    -0.40
     oreilles
    -0.40
     zweiter
    -0.40
     samping
    -0.40
    POSITIVE LOGITS
     tantas
    1.48
     tantos
    1.44
     countless
    1.18
     so
    1.15
     innumerable
    1.10
     tão
    1.09
     begitu
    1.07
     many
    1.03
     tellement
    0.98
     zoveel
    0.97
    Activations Density 1.656%

    No Known Activations