© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8502
    Prev
    Next
    INDEX
    Explanations

    TV and news channel names usually containing numbers and the words Max or Channel

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     doPost
    -0.66
     onAnimation
    -0.63
    numerusform
    -0.63
    Geplaatst
    -0.61
     AttributeSet
    -0.61
     متعلقه
    -0.60
     referenties
    -0.59
    Sucesor
    -0.59
    kmäler
    -0.56
    رشف
    -0.55
    POSITIVE LOGITS
     Scooter
    0.56
    __':
    
    0.56
    '))
    
    0.55
    ']))
    
    0.54
    )):
    
    0.53
    '));
    
    0.53
    (;;)
    0.53
    >";
    
    0.53
    YMMV
    0.50
     Hap
    0.49
    Activations Density 0.046%

    No Known Activations