© 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. 5468
    Prev
    Next
    INDEX
    Explanations

    mentions of Samsung Galaxy products, especially tablets and phones.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon

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

    Mobile devices

    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
     jspb
    -0.60
    mobile
    -0.52
    loài
    -0.50
    ]='\
    -0.49
    alo
    -0.47
    Autoritní
    -0.46
    flat
    -0.45
     app
    -0.45
     mobile
    -0.45
    Mobile
    -0.45
    POSITIVE LOGITS
    udge
    0.63
    AnchorStyles
    0.61
     kasarigan
    0.60
    UIControlState
    0.60
    ChildIndex
    0.59
    phazard
    0.59
    TagHelper
    0.58
    CloseOperation
    0.56
    hasMoreElements
    0.56
    المكان
    0.55
    Activations Density 0.569%

    No Known Activations