© 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. 12141
    Prev
    Next
    INDEX
    Explanations

    conversational text, especially dialogue, and quotes.

    oai_token-act-pair · gemini-2.0-flash

    words beginning with 'i' or variations of 'its'

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

    punctuation

    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
    CloseOperation
    -0.98
     ainfi
    -0.94
     purpoſe
    -0.94
    
    -0.91
     Monfieur
    -0.90
     nahilalakip
    -0.89
    tagext
    -0.89
    ValueStyle
    -0.87
     ſche
    -0.86
    UnsafeEnabled
    -0.86
    POSITIVE LOGITS
     its
    0.70
    its
    0.53
     can
    0.52
    Its
    0.49
     Its
    0.48
     sp
    0.47
    can
    0.46
    '}';
    0.46
    be
    0.45
     I
    0.45
    Activations Density 1.294%

    No Known Activations