© 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. 736
    Prev
    Next
    INDEX
    Explanations

    technical language related to scientific studies including cells, cell lines, and genes.

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    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
    Literatuur
    -0.56
    Джерела
    -0.56
    /')
    -0.52
    География
    -0.51
    omorphism
    -0.50
     }}}
    -0.48
    requestCode
    -0.48
     насељу
    -0.48
    }")
    -0.48
    labus
    -0.48
    POSITIVE LOGITS
    Cursors
    0.63
     Saltar
    0.61
    حياته
    0.57
     Infórmanos
    0.57
     initComponents
    0.55
    LookAnd
    0.55
     preghiera
    0.54
    interopRequire
    0.52
     المعرف
    0.52
    DebuggerNonUser
    0.51
    Activations Density 16.337%

    No Known Activations