© 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. 5377
    Prev
    Next
    INDEX
    Explanations

    the names of a specific type of monster, commonly starting with "Da"

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Da'

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

    Da

    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
     uska
    -0.77
     ComVisible
    -0.77
    ########.
    -0.70
     BoxDecoration
    -0.69
    AccessorTable
    -0.68
    ">//
    -0.68
    RectangleBorder
    -0.68
    WireFormatLite
    -0.66
    ніципалі
    -0.64
    ंदीखरीदारी
    -0.63
    POSITIVE LOGITS
     boss
    0.51
     stat
    0.45
    }();
    0.42
     guide
    0.42
     mis
    0.41
    prepend
    0.40
    Mas
    0.39
    ffy
    0.39
    affaires
    0.39
     जाएगा
    0.39
    Activations Density 0.700%

    No Known Activations