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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    quantities and superlatives

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    +#+#
    -0.56
     FMI
    -0.53
     treu
    -0.49
    SourceChecksum
    -0.48
     conjoint
    -0.47
     AUSSI
    -0.45
     "]";
    -0.44
    KommentareTeilen
    -0.44
    lių
    -0.44
    Karla
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.63
     Савезне
    0.62
     ***!
    0.62
    istoitu
    0.62
    ContentAsync
    0.61
    PerformLayout
    0.58
    XmlAccessType
    0.57
    astify
    0.57
    JspWriter
    0.57
     تضيفلها
    0.56
    Activations Density 2.551%

    No Known Activations