© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1035
    Prev
    Next
    INDEX
    Explanations

    idiomatic expressions and turns of phrase

    oai_token-act-pair · gemini-2.0-flash

    metaphors and idioms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ",
    -0.44
     presidencia
    -0.43
     Pe
    -0.43
     pe
    -0.42
     .
    -0.42
    jeb
    -0.42
     A
    -0.42
    ',
    -0.41
     "
    -0.41
    ,
    -0.41
    POSITIVE LOGITS
    <bos>
    0.98
     الحره
    0.84
     Савезне
    0.83
     EconPapers
    0.83
    脚注の使い方
    0.82
     itſelf
    0.81
    󠁿
    0.81
     myſelf
    0.81
     Efq
    0.81
     utafitiHapana
    0.77
    Activations Density 2.143%

    No Known Activations