© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13221
    Prev
    Next
    INDEX
    Explanations

    the word "invention" and words associated with it.

    oai_token-act-pair · gemini-2.0-flash

    relates

    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
    InputBorder
    -0.90
    ftagPool
    -0.64
     referrerpolicy
    -0.63
     صوتيه
    -0.62
     nawr
    -0.59
    UIControlState
    -0.57
     оригіналу
    -0.56
    TagHelpers
    -0.55
    NullException
    -0.55
    fromCharCode
    -0.54
    POSITIVE LOGITS
     raiſ
    0.50
    ViewImports
    0.50
    ---*/
    0.45
    andaan
    0.43
     uſed
    0.43
    InputTagHelper
    0.42
    <bos>
    0.41
     AssemblyVersion
    0.40
     houſe
    0.40
     myſelf
    0.40
    Activations Density 1.241%

    No Known Activations