© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8070
    Prev
    Next
    INDEX
    Explanations

    source code file information including file names, paths, and build settings

    oai_token-act-pair · gemini-2.0-flash

    file paths and plugins

    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
     po
    -0.80
    ValueStyle
    -0.77
     تضيفلها
    -0.77
     pro
    -0.73
     trans
    -0.72
     op
    -0.71
     par
    -0.69
     reg
    -0.69
    verwijspagina
    -0.68
     pe
    -0.67
    POSITIVE LOGITS
     oogen
    0.64
     dezelve
    0.62
     sandero
    0.60
     handkerchief
    0.59
     marseille
    0.58
     alicante
    0.58
     Declarations
    0.58
     tiegħek
    0.57
     AssertionError
    0.57
     randomization
    0.56
    Activations Density 8.621%

    No Known Activations