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. 14436
    Prev
    Next
    INDEX
    Explanations

    words that indicate a problem or limitation

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    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
     houſe
    -0.97
     فريبيس
    -0.97
    despite
    -0.96
    <?
    -0.94
     pleaſure
    -0.94
     wikipagina
    -0.93
     becauſe
    -0.93
     Monfieur
    -0.92
     Theſe
    -0.92
     ſtate
    -0.91
    POSITIVE LOGITS
    ,
    0.56
     b
    0.56
     M
    0.55
     De
    0.55
     al
    0.55
    <eos>
    0.54
     des
    0.54
    b
    0.54
     v
    0.53
    ib
    0.52
    Activations Density 6.820%

    No Known Activations