© 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. 5458
    Prev
    Next
    INDEX
    Explanations

    sentences that express changes in how things used to be

    oai_token-act-pair · gemini-2.0-flash

    concepts related to the unconventional or extraordinary

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

    rare/uncommon things

    np_max-act-logits · gemini-2.0-flash
    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
    enumii
    -0.71
    HtmlAttribute
    -0.70
    enderror
    -0.67
    ########.
    -0.62
     StatefulWidget
    -0.61
     بيها
    -0.59
    retanto
    -0.57
    )‏
    -0.56
    DebuggerNonUser
    -0.56
     anzi
    -0.56
    POSITIVE LOGITS
     unheard
    0.76
     reserved
    0.71
     thought
    0.64
     considered
    0.63
     unthinkable
    0.57
     rare
    0.54
     domain
    0.54
    modb
    0.53
     taboo
    0.52
     unimaginable
    0.52
    Activations Density 3.895%

    No Known Activations