© 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. 10261
    Prev
    Next
    INDEX
    Explanations

    code related functions, strings, variable names, and logic

    oai_token-act-pair · gemini-2.0-flash

    data types

    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
    entran
    -0.44
    вість
    -0.40
    SequentialGroup
    -0.40
    мане
    -0.40
     Entry
    -0.40
    imer
    -0.39
    vera
    -0.39
    フト
    -0.37
    Entry
    -0.37
    <bos>
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.81
    脚注の使い方
    0.79
    INCREF
    0.70
     ?>/
    0.70
     AssemblyCulture
    0.69
    
    0.68
     disambiguazione
    0.68
    webElementXpaths
    0.65
     oprot
    0.64
    yntaxException
    0.64
    Activations Density 11.230%

    No Known Activations