© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    bureaucratic language related to government regulations and science

    oai_token-act-pair · gemini-2.0-flash

    policy

    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
    HomeAsUpEnabled
    -0.69
    tonsoft
    -0.60
    Flavor
    -0.57
    havior
    -0.56
     Flavor
    -0.56
     NSCoder
    -0.56
     fervor
    -0.55
     clamor
    -0.54
     labors
    -0.54
    UNDLE
    -0.53
    POSITIVE LOGITS
    onViewCreated
    0.63
    mybatisplus
    0.61
     مشين
    0.57
    ⓧ
    0.56
    DebuggerNonUser
    0.56
    findpost
    0.55
    ="{{
    0.54
    lwjgl
    0.53
    scrapy
    0.53
    Ira
    0.52
    Activations Density 19.368%

    No Known Activations