© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases, including pronouns and words related to laws, religion, dragons, and the first instance of something.

    oai_token-act-pair · gemini-2.0-flash

    first

    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
    scriptcase
    -0.62
     written
    -0.57
     ran
    -0.54
    findpost
    -0.54
    ingtones
    -0.52
     proven
    -0.52
    offsetof
    -0.52
    $_['
    -0.51
    written
    -0.50
    кипедия
    -0.50
    POSITIVE LOGITS
     turned
    0.58
    TRIBUN
    0.57
     Turned
    0.57
    turned
    0.54
     excluded
    0.52
    ScopeManager
    0.50
    PYX
    0.50
    सन्दर्भ
    0.49
     ujednoznacz
    0.49
    ernoo
    0.49
    Activations Density 9.843%

    No Known Activations