© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3300
    Prev
    Next
    INDEX
    Explanations

    mentions of dates, common nouns, and proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    Holiday context

    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
    Armed
    -0.54
    armed
    -0.53
     Armed
    -0.52
     armed
    -0.51
    opatho
    -0.48
    substantial
    -0.48
     Waray
    -0.47
    ITRE
    -0.46
    _))
    -0.46
     aeronau
    -0.46
    POSITIVE LOGITS
    Rhestr
    0.66
    fortawesome
    0.65
    AnchorStyles
    0.61
    CodedInputStream
    0.61
     يتيمه
    0.53
     lenker
    0.53
    DockStyle
    0.53
    MENAFN
    0.53
    Lähteet
    0.52
    ConstraintMaker
    0.52
    Activations Density 8.283%

    No Known Activations