© 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. 12483
    Prev
    Next
    INDEX
    Explanations

    text from corporate "About Us" information, especially related to charities, fundraising, or user database management.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon from specialized fields

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

    Business and service descriptions

    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
    хь
    -0.64
     TÉCN
    -0.58
     contactez
    -0.57
     recev
    -0.56
     vierge
    -0.56
     bicchiere
    -0.52
     MUNDO
    -0.52
     pescoço
    -0.52
     LIRE
    -0.52
     acuer
    -0.50
    POSITIVE LOGITS
    
    0.74
    ilever
    0.73
    crollView
    0.66
    ulemon
    0.66
    nteral
    0.66
     mergeFrom
    0.65
    ragalactic
    0.64
    oflavin
    0.63
    addPreferredGap
    0.63
    denly
    0.60
    Activations Density 12.326%

    No Known Activations