© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3945
    Prev
    Next
    INDEX
    Explanations

    words describing physics, relating to balance and force

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     estekak
    -0.72
    出版年
    -0.69
    Hochspringen
    -0.65
    ⓧ
    -0.63
    存于互联网档案馆
    -0.58
    Lähteet
    -0.58
    msgTypes
    -0.58
    DockStyle
    -0.57
     AspNetCore
    -0.56
    featureID
    -0.55
    POSITIVE LOGITS
    inSlope
    0.56
     EnglishChoose
    0.53
    Jeografia
    0.48
    kste
    0.47
     donor
    0.47
     donated
    0.45
    Trains
    0.45
    MLLoader
    0.45
     ORGANISM
    0.44
     wishing
    0.44
    Activations Density 4.775%

    No Known Activations