© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to transferring something or some kind of judgment

    oai_token-act-pair · gemini-2.0-flash

    movement or types

    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
     âmes
    -0.84
     habet
    -0.83
     tää
    -0.81
     perpetuity
    -0.78
     prêtres
    -0.78
     eccl
    -0.77
     statunit
    -0.77
     auroit
    -0.77
     étoit
    -0.75
     larmes
    -0.75
    POSITIVE LOGITS
    にほんブログ村
    0.67
    "):
    0.66
    .},
    0.66
    Demikian
    0.66
     in
    0.65
    Amicalement
    0.63
    diensten
    0.62
    OGND
    0.61
     bpy
    0.61
    -',
    0.60
    Activations Density 3.404%

    No Known Activations