© 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. 12093
    Prev
    Next
    INDEX
    Explanations

    instances of the words "hope" or "favor/favour," sometimes picking up nearby terms

    oai_token-act-pair · gemini-2.0-flash

    preference, advantage

    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
    NUMX
    -0.90
    YMMV
    -0.81
     transfieras
    -0.78
     insofar
    -0.76
    <_>
    -0.75
    ()")
    -0.74
    ItemBackground
    -0.71
    ')}
    -0.71
    sonaro
    -0.70
    ificantly
    -0.70
    POSITIVE LOGITS
     Référence
    0.73
     ruines
    0.68
     spéciaux
    0.57
     atracción
    0.56
     helyez
    0.54
     showcasing
    0.54
     تانيه
    0.53
    不一样的
    0.52
     encargado
    0.52
     shew
    0.52
    Activations Density 0.999%

    No Known Activations