© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    the word "version" and other forms of the word

    oai_token-act-pair · gemini-2.0-flash

    version

    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
     version
    -1.30
     versions
    -1.20
     Version
    -1.09
    version
    -1.04
     VERSION
    -1.03
     versión
    -1.02
     Versions
    -1.01
    Version
    -1.00
     versiones
    -1.00
    Versions
    -0.96
    POSITIVE LOGITS
    oredCriteria
    0.81
     мәкал
    0.77
    WebElementEntity
    0.70
     BoxFit
    0.68
    webElementXpaths
    0.68
    ^(@)
    0.66
    ')):
    0.63
    HandlerContext
    0.61
     ExecuteAsync
    0.61
    staun
    0.61
    Activations Density 6.716%

    No Known Activations