© 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
    2. Gemma-2-2B
    3. 18-GEMMASCOPE-TRANSCODER-16K
    4. 7620
    Prev
    Next
    INDEX
    Explanations

    research or data collection related terms and vocabulary

    oai_token-act-pair · gemini-2.0-flash

    dietary studies and questionnaires

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     صوتيه
    -0.64
     виправивши
    -0.64
    abestanden
    -0.63
    SharedDtor
    -0.63
     estimés
    -0.62
    BagConstraints
    -0.61
    complexType
    -0.61
    enterOuterAlt
    -0.59
    protoimpl
    -0.59
    ollectionView
    -0.59
    POSITIVE LOGITS
    meanor
    0.53
    mäh
    0.51
    ditor
    0.49
     européennes
    0.47
     recollect
    0.47
     exemplu
    0.46
    */].
    0.46
     recall
    0.45
    ьаж
    0.45
     collections
    0.43
    Activations Density 1.923%

    No Known Activations