© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15042
    Prev
    Next
    INDEX
    Explanations

    words related to clothing, gardening, and/or recycling

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     lest
    -0.44
     tanques
    -0.44
    みな
    -0.43
    mom
    -0.42
     garbage
    -0.42
     Trash
    -0.42
     trash
    -0.42
    Alright
    -0.40
     US
    -0.40
    ale
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    Geplaatst
    0.73
     protoimpl
    0.72
     bezeichneter
    0.71
     jScrollPane
    0.66
    hamdu
    0.64
    脚注の使い方
    0.63
    sertation
    0.63
     disambiguazione
    0.63
    лтемелер
    0.63
    Activations Density 0.950%

    No Known Activations