© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10794
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    __':
    -0.78
    mtrl
    -0.63
    出版年
    -0.62
     IndexError
    -0.62
     <<<<<<<<<<<<<<
    -0.60
    URLException
    -0.59
    FunctionFlags
    -0.59
    __':
    -0.58
    gonic
    -0.55
    IOException
    -0.54
    POSITIVE LOGITS
     INTERESAR
    0.47
     excelencia
    0.44
    UrlResolution
    0.42
     dépens
    0.42
    انتهای
    0.41
    Portail
    0.40
    Poloha
    0.40
    blockList
    0.39
     Վերցված
    0.39
    Personensuche
    0.39
    Activations Density 0.423%

    No Known Activations