© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9885
    Prev
    Next
    INDEX
    Explanations

    words related to semiconductors and chip manufacturing

    oai_token-act-pair · gemini-2.0-flash

    technical developments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    podob
    -0.48
     Rhodesia
    -0.47
     Sultan
    -0.46
    TRIBUN
    -0.45
     يتيمه
    -0.45
    batore
    -0.45
     fVar
    -0.44
    PYX
    -0.43
    ristan
    -0.43
    ujan
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.65
     myſelf
    0.60
     Monfieur
    0.59
    ViewFeatures
    0.59
    AnchorStyles
    0.58
    DockStyle
    0.56
    WindowConstants
    0.56
    KEYCODE
    0.55
    StoryboardSegue
    0.54
    IntoConstraints
    0.54
    Activations Density 23.316%

    No Known Activations