© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15921
    Prev
    Next
    INDEX
    Explanations

    the words "net" and "rate", and possibly also recognizes the phrase ".NET"

    oai_token-act-pair · gemini-2.0-flash

    net

    np_max-act · gemini-2.0-flash

    ▁net

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.83
     and
    -0.91
     the
    -0.68
     or
    -0.59
     of
    -0.57
     in
    -0.52
     le
    -0.49
     is
    -0.49
    def
    -0.48
     are
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.84
     anaemia
    0.82
    DoubleQuotes
    0.73
     Anemia
    0.71
     pretence
    0.71
    Datuak
    0.71
     Manners
    0.71
     Monfieur
    0.70
     Abdomen
    0.70
    MethodManager
    0.69
    Activations Density 2.797%

    No Known Activations