© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5485
    Prev
    Next
    INDEX
    Explanations

    words related to legalities, armed forces, future events and transition, and feelings.

    oai_token-act-pair · gemini-2.0-flash

    waiting and armed forces

    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
    expandindo
    -0.94
     مشين
    -0.87
    脚注の使い方
    -0.70
    сылкі
    -0.69
    makeText
    -0.68
    verwijspagina
    -0.67
     insuffisamment
    -0.63
    dy
    -0.60
    findpost
    -0.58
    ly
    -0.57
    POSITIVE LOGITS
     étoit
    0.64
     samenwerking
    0.64
     bénévoles
    0.64
     femininos
    0.63
    unpublished
    0.63
     purpoſe
    0.63
     roulant
    0.63
     osserva
    0.62
     ſtre
    0.62
     énergétique
    0.61
    Activations Density 1.556%

    No Known Activations