© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13169
    Prev
    Next
    INDEX
    Explanations

    the word 'of' along with massage related terms

    oai_token-act-pair · gemini-2.0-flash

    worship and self devotion

    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
    AnimationsModule
    -0.66
    ⓧ
    -0.65
    MENAFN
    -0.65
    клопе
    -0.65
    Carriera
    -0.64
    
    -0.64
     chi̍t
    -0.64
    Abitanti
    -0.61
     UIAlert
    -0.61
     CGPoint
    -0.61
    POSITIVE LOGITS
    احث
    0.46
    లాలు
    0.45
    IsInitialized
    0.43
     clínico
    0.41
     tű
    0.41
    Whi
    0.41
     linkovi
    0.40
     Rein
    0.40
    Pas
    0.39
    initComponents
    0.39
    Activations Density 0.865%

    No Known Activations