© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11835
    Prev
    Next
    INDEX
    Explanations

    terms used in software code such as "assembly", "using", "namespace", and "license"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    code identifiers

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    •i_pledge_allegiance_to_the:be99c38c-fb55-580f-a218-fae54fc8360f
    Top frequency features for prompt

    No Comments

    Negative Logits
     betweenstory
    -2.56
    WithIOException
    -2.31
    RegressionTest
    -2.20
    ьаж
    -2.19
     propOrder
    -2.17
    GEBURTSDATUM
    -2.16
    IndentedString
    -2.11
     disambiguazione
    -2.11
    DockStyle
    -2.08
     CreateTagHelper
    -2.06
    POSITIVE LOGITS
    <bos>
    1.47
     
    1.29
    '
    1.23
    ↵↵
    1.22
    ,
    1.14
    ↵
    1.08
    ’
    1.05
    .
    1.02
     in
    1.01
     the
    0.95
    Activations Density 29.459%

    No Known Activations