© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12233
    Prev
    Next
    INDEX
    Explanations

    question and answer formatting or code formatting in a conversation.

    oai_token-act-pair · gemini-2.0-flash

    symbols, likely related to programming or data structures

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

    rare tokens

    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
    iden
    -0.56
    “
    -0.56
    mi
    -0.55
    misi
    -0.55
    ‘
    -0.52
     bandoulière
    -0.52
    Dic
    -0.52
    OwnProperty
    -0.49
    |
    -0.49
    .
    -0.49
    POSITIVE LOGITS
    TagMode
    0.92
     виправивши
    0.92
     الدولى
    0.88
     مرئيه
    0.88
    __':
    
    0.87
    énario
    0.81
    "]];
    0.79
    ).)
    0.76
     дописавши
    0.75
    WithMany
    0.75
    Activations Density 0.975%

    No Known Activations