© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15726
    Prev
    Next
    INDEX
    Explanations

    the word "original"

    oai_token-act-pair · gemini-2.0-flash

    original

    np_max-act · gemini-2.0-flash
    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
     CreateTagHelper
    -1.39
     تضيفلها
    -1.33
     חיצוניים
    -1.31
     Theſe
    -1.30
     Efq
    -1.24
     Monfieur
    -1.23
     fewest
    -1.21
    tvguidetime
    -1.21
     HasFactory
    -1.20
     estekak
    -1.19
    POSITIVE LOGITS
    ↵
    0.71
    ,
    0.71
    ↵↵
    0.69
     recently
    0.68
     material
    0.67
     pre
    0.63
     and
    0.63
     strong
    0.63
     in
    0.62
    </u>
    0.62
    Activations Density 2.587%

    No Known Activations