Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14466
    Prev
    Next
    INDEX
    Explanations

    German sentences with the word "hätte" and words around it

    oai_token-act-pair · gemini-2.0-flash

    Varied foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TestingModule
    -0.88
     estekak
    -0.66
    WriteLiteral
    -0.58
    /*
    -0.56
     tast
    -0.53
     XMLHttpRequest
    -0.52
    BagLayout
    -0.52
    RowCount
    -0.51
    FailureListener
    -0.51
     Goya
    -0.51
    POSITIVE LOGITS
    oredCriteria
    0.64
    पया
    0.61
    Palmar
    0.52
     Oat
    0.52
    voyer
    0.48
    
    0.48
    levance
    0.48
     Brownie
    0.47
     jäsen
    0.46
    cemic
    0.45
    Activations Density 0.170%

    No Known Activations