© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12528
    Prev
    Next
    INDEX
    Explanations

    software packages used for data analysis

    oai_token-act-pair · gemini-2.0-flash

    statistical analysis software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Vidite
    -0.85
     betweenstory
    -0.76
     unknownFields
    -0.69
    клопе
    -0.69
    DeleteBehavior
    -0.68
    TagHelper
    -0.67
    ANDUM
    -0.67
     AssemblyCulture
    -0.66
    :])
    -0.65
    UrlResolution
    -0.65
    POSITIVE LOGITS
    {{{
    0.46
     PeEnEo
    0.44
     Đình
    0.43
    ंदीखरीदारी
    0.42
    thur
    0.42
     lateinit
    0.41
     Versammlung
    0.41
     صوتيه
    0.41
    贯
    0.40
     presta
    0.40
    Activations Density 1.197%

    No Known Activations