© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4378
    Prev
    Next
    INDEX
    Explanations

    references to the beginning of a new year

    oai_token-act-pair · gemini-2.0-flash

    new year beginnings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    see
    -1.08
     see
    -1.05
     See
    -1.05
    See
    -1.04
     sees
    -0.77
     SEE
    -0.69
     seeing
    -0.68
    SEE
    -0.63
     saw
    -0.62
     seen
    -0.57
    POSITIVE LOGITS
    ThroughAttribute
    1.19
    oredCriteria
    1.06
    AddTagHelper
    1.04
    IsMutable
    0.96
     متعلقه
    0.93
     protoimpl
    0.93
     AssemblyCompany
    0.89
    StoryboardSegue
    0.87
     millennium
    0.84
     Infórmanos
    0.84
    Activations Density 0.699%

    No Known Activations