© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9669
    Prev
    Next
    INDEX
    Explanations

    words broadly related to reading, examining, or studying something

    oai_token-act-pair · gemini-2.0-flash

    Code and project descriptions

    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
     purpoſe
    -0.71
    исленность
    -0.69
    MigrationBuilder
    -0.66
     Administrativna
    -0.65
     للاسماء
    -0.64
     resourceCulture
    -0.64
    astéroïdes
    -0.63
     myſelf
    -0.62
    InputBorder
    -0.62
    ècie
    -0.61
    POSITIVE LOGITS
     to
    0.67
    RefNanny
    0.54
     einzu
    0.52
    lain
    0.46
     endlessly
    0.46
    AppRoutingModule
    0.44
     and
    0.43
    ModelSerializer
    0.43
     Cowan
    0.43
    impinan
    0.43
    Activations Density 38.420%

    No Known Activations