© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10672
    Prev
    Next
    INDEX
    Explanations

    phrases, clauses, or sentences that are descriptive and/or tell a story, and sometimes numbers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    soort
    -0.52
     Cordero
    -0.51
    libft
    -0.50
     relatifs
    -0.48
     disambiguazione
    -0.47
     أعلام
    -0.47
     HttpNotFound
    -0.47
     Movimento
    -0.47
     Lightfoot
    -0.46
    ลา
    -0.45
    POSITIVE LOGITS
    RunAsync
    0.67
    InputBorder
    0.64
    IBOutlet
    0.61
     NgModule
    0.60
     كومونز
    0.57
     protoimpl
    0.56
    MemoryWarning
    0.56
    NgModule
    0.56
     Rans
    0.53
    onViewCreated
    0.53
    Activations Density 3.599%

    No Known Activations