© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4861
    Prev
    Next
    INDEX
    Explanations

    references to locations, public transit, or related concepts

    oai_token-act-pair · gemini-2.0-flash

    foreign names/words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Swiss
    -1.75
    Swiss
    -1.59
     swiss
    -1.51
     Switzerland
    -1.48
     Wisconsin
    -1.46
     milk
    -1.45
     Milk
    -1.38
    Wisconsin
    -1.35
     WISCONSIN
    -1.34
    Milk
    -1.32
    POSITIVE LOGITS
     Доб
    0.53
     становника
    0.50
     Dob
    0.46
     schä
    0.46
     iconLine
    0.46
     Haig
    0.46
     сей
    0.45
     доб
    0.45
     orec
    0.45
    ərb
    0.44
    Activations Density 1.411%

    No Known Activations