© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2756
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and markers related to teaching and analyzing news, especially fake news, in an educational setting

    oai_token-act-pair · gemini-2.0-flash

    fake or false information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AttributeSet
    -0.85
    InvalidProtocol
    -0.73
    ChildScrollView
    -0.68
    FunctionFlags
    -0.63
    Hentet
    -0.63
    Autoritní
    -0.63
     bezeichneter
    -0.62
    MENAFN
    -0.59
    بوابة
    -0.57
    __":
    -0.56
    POSITIVE LOGITS
    tanleria
    0.54
    ьаж
    0.54
    boda
    0.50
     bParam
    0.49
    Modifiers
    0.47
     Inventories
    0.47
     organizer
    0.46
     utafitiHapana
    0.46
     encomp
    0.45
     Relaciones
    0.45
    Activations Density 6.802%

    No Known Activations