© 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. 9908
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to poverty/poor conditions, manual labor, and suggestive content.

    oai_token-act-pair · gemini-2.0-flash

    mud

    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
    ientôt
    -0.71
    sterone
    -0.63
    disambiguation
    -0.62
    ordinaire
    -0.62
    — 
    -0.59
    ORGANIZATION
    -0.58
    — 
    -0.58
     automaker
    -0.57
     NSCoder
    -0.56
     nonprofit
    -0.55
    POSITIVE LOGITS
    <bos>
    2.08
     ouverts
    0.51
     للمعارف
    0.51
     vastaan
    0.48
     rodea
    0.48
    SourceChecksum
    0.47
     itſelf
    0.47
     prosegu
    0.46
     ouvertes
    0.45
    Autoritní
    0.44
    Activations Density 1.932%

    No Known Activations