© 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. 13181
    Prev
    Next
    INDEX
    Explanations

    action verbs often related to speaking

    oai_token-act-pair · gemini-2.0-flash

    actions

    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
     насељу
    -0.61
    MLLoader
    -0.59
    '.$
    -0.51
    ']='
    -0.50
    CrossRef
    -0.50
    BorderLayout
    -0.49
    ']=='
    -0.48
    esgue
    -0.48
    ")==
    -0.48
    bower
    -0.48
    POSITIVE LOGITS
    nių
    0.56
    Datuak
    0.52
    jestel
    0.51
     disponibilités
    0.51
    tection
    0.49
    tojas
    0.49
     Farewell
    0.47
     survie
    0.47
     ито
    0.46
    paramref
    0.46
    Activations Density 20.150%

    No Known Activations