© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    legal or financial terms.

    oai_token-act-pair · gemini-2.0-flash

    security

    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
    •security

    No Comments

    Negative Logits
     defaultstate
    -0.71
     defaulted
    -0.63
     ComVisible
    -0.62
    Personendaten
    -0.61
    enumii
    -0.59
    IBOutlet
    -0.59
     Default
    -0.59
    tagext
    -0.58
     kasarigan
    -0.58
    তথ্যসূত্র
    -0.57
    POSITIVE LOGITS
    security
    0.65
     security
    0.64
     protoimpl
    0.61
    Security
    0.58
     Security
    0.54
     ged
    0.50
     ujednoznacz
    0.47
     SECURITY
    0.46
    amazonaws
    0.46
    uba
    0.46
    Activations Density 2.824%

    No Known Activations