© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11913
    Prev
    Next
    INDEX
    Explanations

    personal reflections and storytelling

    oai_token-act-pair · gemini-2.0-flash

    past tense auxiliary verbs

    np_token-act-pair-logits · gpt-4o-mini

    pronouns

    np_max-act-logits · gemini-2.0-flash

    personal pronouns

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -0.74
    tvguidetime
    -0.68
    <?
    -0.67
    อนไลน์
    -0.63
    󠁢
    -0.58
    esgue
    -0.57
    тистика
    -0.54
    美味しいです
    -0.53
    せます
    -0.52
     PackageManager
    -0.52
    POSITIVE LOGITS
     had
    1.20
     could
    0.99
    Had
    0.97
    had
    0.96
     Had
    0.92
     was
    0.89
     hadn
    0.89
     HAD
    0.83
     knew
    0.80
     Was
    0.80
    Activations Density 4.479%

    No Known Activations