© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    words related to illness and physical health

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical related text

    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
    =$?
    -0.58
    tagext
    -0.56
    égias
    -0.55
     SwitchCompat
    -0.53
    mány
    -0.53
    RTEX
    -0.53
    BeginContext
    -0.52
    primes
    -0.52
    IndentedString
    -0.51
     Tribun
    -0.50
    POSITIVE LOGITS
     <>",
    0.74
     незавершена
    0.57
     estekak
    0.54
    Hochspringen
    0.54
     chí
    0.52
    MigrationBuilder
    0.51
    انجليز
    0.51
    aarrggbb
    0.50
     otomatig
    0.49
    __[
    0.49
    Activations Density 16.135%

    No Known Activations